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. 24075
    Prev
    Next
    INDEX
    Explanations

    Rust programming language

    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
    system
    -0.08
    Volume
    -0.07
    Ult
    -0.07
    そして
    -0.07
    Menus
    -0.07
     parms
    -0.07
    Constants
    -0.07
    Bin
    -0.06
    são
    -0.06
    𝑡
    -0.06
    POSITIVE LOGITS
    擎
    0.08
     slogan
    0.07
     enraged
    0.07
    的日子
    0.07
    蚁
    0.07
     singles
    0.07
     часто
    0.07
     Dane
    0.07
    -olds
    0.07
     фин
    0.07
    Activations Density 0.014%

    No Known Activations