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. 109775
    Prev
    Next
    INDEX
    Explanations

    since

    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
     upheld
    -0.07
    넣
    -0.07
    Laugh
    -0.07
    トラブル
    -0.07
    messages
    -0.07
    记者表示
    -0.07
    ="{{$
    -0.07
    佩服
    -0.07
    てくれる
    -0.07
     Pdf
    -0.07
    POSITIVE LOGITS
     plant
    0.08
    caf
    0.07
    비
    0.07
     awareness
    0.07
    .getIndex
    0.07
    centers
    0.07
    Cisco
    0.07
     sec
    0.07
    __.__
    0.07
    xe
    0.07
    Activations Density 0.081%

    No Known Activations