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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    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. 19-RESID-POST-AA
    6. 59891
    Prev
    Next
    INDEX
    Explanations

    2

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-qwen2.5-7b-instruct/resid_post_layer_19/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.19.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Nam
    -0.07
    نسب
    -0.07
    申请
    -0.07
    Italy
    -0.07
    橘
    -0.07
     anderen
    -0.07
     rsa
    -0.07
    毕
    -0.07
    人類
    -0.07
     nos
    -0.06
    POSITIVE LOGITS
     UIResponder
    0.08
    draulic
    0.07
     Calls
    0.07
    俗称
    0.07
     Builds
    0.07
     componentWillUnmount
    0.07
    logs
    0.06
    层出
    0.06
    ylum
    0.06
     Matcher
    0.06
    Activations Density 0.005%

    No Known Activations