© 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. 23-TRANSCODER-HP
    7. 24948
    Prev
    Next
    INDEX
    Explanations

    in spite of, irrespective

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_23.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.23.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ekt
    -0.31
    æŁĶ
    -0.29
    Ñĥз
    -0.26
    ä¹ł
    -0.25
    inston
    -0.25
    angi
    -0.24
     lessons
    -0.24
    ii
    -0.24
    éĽĨ
    -0.23
    s
    -0.23
    POSITIVE LOGITS
    çħ§æł·
    0.36
    æĪijè¿ĺæĺ¯
    0.27
    _given
    0.26
    /Q
    0.26
    éļ¾
    0.25
     thereof
    0.24
    /or
    0.24
    æĥħåĨµæĿ¥çľĭ
    0.24
     nevertheless
    0.23
    [float
    0.23
    Activations Density 0.050%

    No Known Activations