© 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. 9903
    Prev
    Next
    INDEX
    Explanations

    exclusion/removal

    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
    èĥ¤
    -0.26
    tau
    -0.26
     sour
    -0.25
    anks
    -0.25
     tau
    -0.24
     k
    -0.24
     overst
    -0.23
     kappa
    -0.23
    baru
    -0.23
     Consort
    -0.23
    POSITIVE LOGITS
    çªĹå¤ĸ
    0.42
    ä¹ĭå¤ĸ
    0.41
     outside
    0.41
    æł¡å¤ĸ
    0.40
     Outside
    0.39
    室å¤ĸ
    0.39
    åĩºå¢ĥ
    0.37
    outside
    0.35
    Away
    0.34
    Outside
    0.34
    Activations Density 0.003%

    No Known Activations