© 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. 76347
    Prev
    Next
    INDEX
    Explanations

    feature

    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
    _lens
    -0.07
    ТЬ
    -0.07
    ут
    -0.07
     :]
    -0.07
     основном
    -0.07
    \)
    -0.07
    .']
    -0.07
    _vlog
    -0.07
    .Batch
    -0.06
    $out
    -0.06
    POSITIVE LOGITS
     brand
    0.07
     printed
    0.07
     altern
    0.06
    естественн
    0.06
    ocom
    0.06
     Cr
    0.06
    𦰡
    0.06
     }}"><
    0.06
    Implicit
    0.06
     الن
    0.06
    Activations Density 0.014%

    No Known Activations