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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-4B
    5. 27-TRANSCODER-HP
    7. 57252
    Prev
    Next
    INDEX
    Explanations

    professional contexts

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_27.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.27.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Licence
    -0.32
     lodge
    -0.29
     licence
    -0.28
    вел
    -0.26
    licence
    -0.26
    oger
    -0.26
     Saud
    -0.25
     lic
    -0.24
     convers
    -0.24
    èĢģ人家
    -0.24
    POSITIVE LOGITS
    éĺĹ
    0.30
    ButtonDown
    0.26
     flushing
    0.25
    PERT
    0.25
    åŁĭ
    0.25
    StartPosition
    0.25
    ETO
    0.24
    uto
    0.24
    erah
    0.24
    lems
    0.24
    Activations Density 0.003%

    No Known Activations