© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    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. 8599
    Prev
    Next
    INDEX
    Explanations

    product sales/distribution

    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
    ámara
    -0.07
    簠
    -0.07
    为核心的
    -0.07
    蒇
    -0.07
    .pix
    -0.06
     similarity
    -0.06
    ями
    -0.06
    (fullfile
    -0.06
    MainFrame
    -0.06
    iminal
    -0.06
    POSITIVE LOGITS
    呼
    0.07
     unpublished
    0.07
    港口
    0.07
    拭
    0.07
    דח
    0.07
     hạ
    0.06
    斛
    0.06
    㶲
    0.06
    pref
    0.06
    啜
    0.06
    Activations Density 0.072%

    No Known Activations