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. 27308
    Prev
    Next
    INDEX
    Explanations

    XML declarations

    np_max-act · gemini-2.0-flash
    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
    係
    -0.09
    重启
    -0.07
    kręc
    -0.07
     mł
    -0.07
    .Mode
    -0.07
    试题
    -0.07
    被列入
    -0.07
     主
    -0.07
    可持续
    -0.07
    ⓨ
    -0.07
    POSITIVE LOGITS
    -largest
    0.07
    many
    0.07
    蜩
    0.07
     scalar
    0.07
    	init
    0.07
     hates
    0.07
    海淀区
    0.07
    _definitions
    0.07
     designation
    0.07
    expire
    0.06
    Activations Density 0.001%

    No Known Activations