© 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. 8037
    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
    gmt
    -0.27
    è¿ĺ好
    -0.27
    ä½Ĩä»į
    -0.26
     scal
    -0.25
    è¿«ä¸įåıĬå¾ħ
    -0.24
     além
    -0.24
    翻身
    -0.24
    HeaderView
    -0.24
    è¿ĺèĥ½
    -0.24
    èī¾æ»ĭ
    -0.23
    POSITIVE LOGITS
    æŁIJç§į
    0.52
    æŁIJç§įç¨ĭ度
    0.41
     somehow
    0.40
    æŁIJ
    0.36
     somew
    0.35
    æŁIJ个
    0.33
     somewhere
    0.33
     sense
    0.32
     in
    0.32
     Sense
    0.31
    Activations Density 0.004%

    No Known Activations