© 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
    3. Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
    5. Qwen2.5-7B-IT
    7. Resid Post - 131k
    9. 11-RESID-POST-AA
    11. 91912
    Prev
    Next
    INDEX
    Explanations

    sexual content

    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
     ...\
    -0.07
    ="↵
    -0.07
    南宁市
    -0.07
     ///↵
    -0.07
    inch
    -0.07
     institutions
    -0.07
     lawyers
    -0.07
    zion
    -0.07
     Armenian
    -0.06
     Riy
    -0.06
    POSITIVE LOGITS
    ulum
    0.08
    ibbean
    0.07
    (typeof
    0.07
    .adjust
    0.07
     proces
    0.06
     sl
    0.06
    bles
    0.06
    .prod
    0.06
    累计
    0.06
    口味
    0.06
    Activations Density 0.051%

    No Known Activations