© 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. 57216
    Prev
    Next
    INDEX
    Explanations

    in

    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
     gener
    -0.30
     computing
    -0.27
    comput
    -0.26
    æĶ¹åĬ¨
    -0.26
    å¿łå®ŀ
    -0.25
     TSR
    -0.25
     programm
    -0.25
    (mut
    -0.24
     normally
    -0.24
     reputation
    -0.24
    POSITIVE LOGITS
    avana
    0.32
    ç½IJ
    0.31
    jiang
    0.30
     Bosnia
    0.27
    è¦ģåģļ
    0.27
    <?,
    0.27
    _MATCH
    0.26
     onRequest
    0.26
     xrange
    0.25
    Ut
    0.25
    Activations Density 0.009%

    No Known Activations