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. 59719
    Prev
    Next
    INDEX
    Explanations

    scientific/technical measurements

    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
    -quarter
    -0.07
     Struct
    -0.07
     userList
    -0.07
    ߦ
    -0.07
     IsNot
    -0.07
     Stateless
    -0.07
    izu
    -0.07
    >O
    -0.07
    =k
    -0.06
    骛
    -0.06
    POSITIVE LOGITS
    Flow
    0.07
     Tank
    0.07
    حسب
    0.07
     בתוך
    0.07
     dim
    0.07
    .batch
    0.07
     kitty
    0.07
    once
    0.07
     digs
    0.07
     милли
    0.07
    Activations Density 0.020%

    No Known Activations