© 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. 8303
    Prev
    Next
    INDEX
    Explanations

    Cle

    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
     keeper
    -0.30
    é»ijèī²
    -0.26
    .same
    -0.26
    /json
    -0.25
    Keeper
    -0.24
    ooks
    -0.24
     prime
    -0.24
    [attr
    -0.24
    .ov
    -0.24
    å°Ĩè¿Ľä¸ĢæŃ¥
    -0.24
    POSITIVE LOGITS
    visible
    0.27
    æī§ä¸ļ
    0.27
    esis
    0.25
     Visible
    0.25
    êm
    0.24
    ä¸ĢæĹ¥
    0.24
    çĥĿ
    0.24
    Visible
    0.24
    lip
    0.23
    volatile
    0.23
    Activations Density 0.904%

    No Known Activations