© 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. 25-TRANSCODER-HP
    7. 108251
    Prev
    Next
    INDEX
    Explanations

    told

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_25.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.25.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    å¾Ĺ好
    -0.28
    å¼ķ
    -0.27
    å¾Ĺå¾Ī好
    -0.27
    éĹŃ
    -0.26
    éĢ¼
    -0.26
    é©®
    -0.26
    æĮŁ
    -0.26
    usc
    -0.25
     us
    -0.25
     Literal
    -0.25
    POSITIVE LOGITS
    éĩĩåıĸ
    0.28
    ä¿ĿçķĻ
    0.28
    å®Įç¾İçļĦ
    0.26
     Doub
    0.26
    teness
    0.26
     punct
    0.26
    enment
    0.25
    æĭĻ
    0.24
    å®Įç¾İ
    0.24
    ignet
    0.24
    Activations Density 0.195%

    No Known Activations