© 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. 14-TRANSCODER-HP
    7. 40338
    Prev
    Next
    INDEX
    Explanations

    Jr or Sr

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_14.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.14.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Vill
    -0.28
    è·µ
    -0.27
    olla
    -0.26
    以èī²
    -0.25
    æī¦
    -0.24
    æ°´å¹³
    -0.24
    á¿ĸ
    -0.24
     interpre
    -0.24
    ä¸įæĪIJ
    -0.23
    ustr
    -0.23
    POSITIVE LOGITS
    MG
    0.28
     uploaded
    0.27
    bred
    0.26
    Estimated
    0.26
    eken
    0.25
     uploading
    0.25
     uploads
    0.25
    bsite
    0.24
     backgrounds
    0.24
    ä¼°ç®Ĺ
    0.24
    Activations Density 1.064%

    No Known Activations