Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
    3. Qwen2.5-7B-IT
    4. Resid Post - 131k
    5. 15-RESID-POST-AA
    6. 115135
    Prev
    Next
    INDEX
    Explanations

    1

    np_max-act · gemini-2.0-flash

    numeric tokens—especially decimals, prices, measurements, and alphanumeric model or reference codes within product-style text.

    oai_token-act-pair · gpt-5Triggered by @vetterc0
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-qwen2.5-7b-instruct/resid_post_layer_15/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.15.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     sommes
    -0.07
    Winter
    -0.07
    入围
    -0.07
    �
    -0.07
    官方
    -0.07
     festival
    -0.06
    ivel
    -0.06
    ome
    -0.06
    镌
    -0.06
    达人
    -0.06
    POSITIVE LOGITS
    chron
    0.07
    برش
    0.07
     Prob
    0.07
     abrupt
    0.07
    church
    0.06
    (pro
    0.06
     прав
    0.06
    �
    0.06
    ripp
    0.06
    迈出
    0.06
    Activations Density 0.367%

    No Known Activations