© 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. 35-TRANSCODER-HP
    7. 39754
    Prev
    Next
    INDEX
    Explanations

    Technical writing/references

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_35.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.35.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    åİ»çľĭ
    -0.28
     SHALL
    -0.27
    ä½Ļ家
    -0.26
    éĴ¤
    -0.24
    еÑģÑĤеÑģÑĤв
    -0.24
    æľĢéķ¿
    -0.24
     parfait
    -0.23
    :\/\/
    -0.23
    elage
    -0.23
    ili
    -0.23
    POSITIVE LOGITS
    apolis
    0.34
    ador
    0.34
    ANA
    0.33
    m
    0.33
    andin
    0.32
    avia
    0.32
    aby
    0.31
    aha
    0.31
    ahan
    0.31
    arton
    0.31
    Activations Density 1.550%

    No Known Activations