© 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. 25-TRANSCODER-HP
    7. 109515
    Prev
    Next
    INDEX
    Explanations

    commas

    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
    Negative Logits
    repid
    -0.28
     oct
    -0.28
    使人
    -0.25
    endency
    -0.25
    被人
    -0.24
    ÙĦØ·
    -0.24
    ém
    -0.23
    acts
    -0.23
    spy
    -0.23
    ä¸įåģļ
    -0.23
    POSITIVE LOGITS
    å®ĥ
    0.31
    好åIJĹ
    0.29
    横åIJij
    0.28
    ANEL
    0.27
    It
    0.27
    ãģ«ãĤĪ
    0.27
    请éĹ®
    0.26
     yarg
    0.26
     It
    0.26
    å®ĥ们
    0.26
    Activations Density 1.113%

    No Known Activations