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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 110500
    Prev
    Next
    INDEX
    Explanations

    number

    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
     món
    -0.07
    annonce
    -0.07
     Judith
    -0.07
    奇特
    -0.07
     תו
    -0.07
    撰
    -0.07
     zb
    -0.06
    촐
    -0.06
    gradation
    -0.06
    ('_',
    -0.06
    POSITIVE LOGITS
    য
    0.07
     Affairs
    0.07
    ϰ
    0.07
     servic
    0.07
    Steel
    0.06
     stage
    0.06
    ам
    0.06
    .FromArgb
    0.06
    -haired
    0.06
     defenders
    0.06
    Activations Density 0.003%

    No Known Activations