© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-4B
    5. 27-TRANSCODER-HP
    7. 57965
    Prev
    Next
    INDEX
    Explanations

    Museum or gallery

    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
     Derived
    -0.29
    åħ¨æĹ¥
    -0.29
    æĺ¼
    -0.28
     Floors
    -0.28
    енÑĮ
    -0.26
    話
    -0.26
    elist
    -0.25
    -doc
    -0.25
     floors
    -0.25
    éĹº
    -0.25
    POSITIVE LOGITS
    CONS
    0.30
    atch
    0.25
    æľĪä¸Ń
    0.25
    vers
    0.24
    subpackage
    0.24
    cons
    0.24
     inconsist
    0.24
    èĪĮ头
    0.24
     acab
    0.24
     contradiction
    0.24
    Activations Density 1.098%

    No Known Activations