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. 11-RESID-POST-AA
    6. 61806
    Prev
    Next
    INDEX
    Explanations

    Double-edged situations

    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_11/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.11.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     teşek
    -0.08
    ﱔ
    -0.07
    ToggleButton
    -0.07
    _COLOR
    -0.07
     textures
    -0.06
    _Property
    -0.06
    葳
    -0.06
    torrent
    -0.06
    Ș
    -0.06
    =Value
    -0.06
    POSITIVE LOGITS
     Sick
    0.07
    在路上
    0.07
    하였습니다
    0.07
     />';↵
    0.07
    _information
    0.07
    诂
    0.06
     experimental
    0.06
    /in
    0.06
    jections
    0.06
     deceit
    0.06
    Activations Density 0.076%

    No Known Activations