© 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. 7682
    Prev
    Next
    INDEX
    Explanations

    River

    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
    everything
    -0.31
    itics
    -0.31
     everything
    -0.28
    ISTER
    -0.28
    齿轮
    -0.28
     gear
    -0.28
    qed
    -0.27
     conv
    -0.27
    (power
    -0.26
    Everything
    -0.25
    POSITIVE LOGITS
    erton
    0.27
    .Skin
    0.24
    诣
    0.24
    idas
    0.23
    æıIJåĩºçļĦ
    0.23
     Exped
    0.23
    éĢģä¸Ĭ
    0.23
    è§Ĥ念
    0.23
    åħ¥å¸Ĥ
    0.23
     bÃłi
    0.23
    Activations Density 0.937%

    No Known Activations