© 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
    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. 21104
    Prev
    Next
    INDEX
    Explanations

    sexual acts

    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
    晋江
    -0.08
     noble
    -0.07
    园区
    -0.07
    xi
    -0.07
    โม
    -0.07
    магазине
    -0.07
    auction
    -0.07
    PN
    -0.07
     역
    -0.07
     Destination
    -0.06
    POSITIVE LOGITS
    PLIT
    0.08
     widen
    0.07
    盹
    0.07
    延期
    0.07
    phan
    0.07
    DOG
    0.07
    _episode
    0.07
    正常使用
    0.07
     blow
    0.07
    .LocalDate
    0.06
    Activations Density 0.148%

    No Known Activations