© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-4B
    5. 27-TRANSCODER-HP
    7. 56510
    Prev
    Next
    INDEX
    Explanations

    To

    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
    Negative Logits
    好åIJĹ
    -0.30
    为ä»Ģä¹Ī
    -0.28
    ä½ķ
    -0.27
    æŁ°
    -0.26
    å¦Ĥä½ķ
    -0.26
    为ä»Ģä¹Īä¸į
    -0.26
    dq
    -0.25
    Fs
    -0.25
    æĢİä¹Īåģļ
    -0.25
     favour
    -0.25
    POSITIVE LOGITS
     further
    0.35
    è¿Ľä¸ĢæŃ¥
    0.31
    exact
    0.31
     thing
    0.30
     things
    0.30
    羣æŃ£
    0.30
    äºĭæĥħ
    0.28
     simpl
    0.28
    URT
    0.28
    å½»åºķ
    0.28
    Activations Density 0.002%

    No Known Activations