© 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. 9-TRANSCODER-HP
    7. 30005
    Prev
    Next
    INDEX
    Explanations

    ell

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_9.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.9.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    è¿ľ
    -0.28
    aira
    -0.27
     far
    -0.27
    jian
    -0.27
    Nu
    -0.27
    ink
    -0.27
    nu
    -0.26
    åIJĪä¸Ģ
    -0.26
    åIJĪæĪIJ
    -0.26
    壳
    -0.26
    POSITIVE LOGITS
    baugh
    0.27
     Guerrero
    0.26
    ä½łçŁ¥éģĵ
    0.26
    è±ī
    0.26
    пÑĢом
    0.26
     thous
    0.25
     unsus
    0.25
    ibus
    0.25
     autonom
    0.24
    osas
    0.24
    Activations Density 0.343%

    No Known Activations