© 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. 19-RESID-POST-AA
    11. 8993
    Prev
    Next
    INDEX
    Explanations

    unusual

    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
     screened
    -0.07
    签字
    -0.07
    当即
    -0.07
    ********************************************************************************
    -0.07
     Pat
    -0.07
    xcf
    -0.07
    私自
    -0.07
     vast
    -0.07
    清净
    -0.07
    票
    -0.07
    POSITIVE LOGITS
     unusual
    0.09
     الع
    0.08
     Renaissance
    0.07
    隆
    0.07
    (re
    0.07
    asa
    0.07
    轺
    0.07
    _full
    0.07
     usual
    0.07
    song
    0.06
    Activations Density 0.005%

    No Known Activations