© 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. 9231
    Prev
    Next
    INDEX
    Explanations

    Refusal

    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
    strt
    -0.30
    realloc
    -0.26
     redraw
    -0.25
     strt
    -0.25
     darkest
    -0.25
    ãĥ¼ãĤ·
    -0.24
    dae
    -0.24
    mpl
    -0.24
    lp
    -0.24
    (_.
    -0.23
    POSITIVE LOGITS
    éģĵè·¯
    0.27
    å½ĵåį³
    0.26
     leve
    0.26
    gaard
    0.26
    åĩºå¸Ńä¼ļè®®
    0.25
     speakers
    0.25
    åŀĮ
    0.25
    veal
    0.25
     mockery
    0.25
     mothers
    0.24
    Activations Density 0.003%

    No Known Activations