© 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. 30-TRANSCODER-HP
    7. 95500
    Prev
    Next
    INDEX
    Explanations

    Start or end of period

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_30.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.30.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     early
    -0.41
     week
    -0.41
    æĹ©
    -0.39
     Early
    -0.36
    Early
    -0.34
    early
    -0.34
    week
    -0.34
     Week
    -0.33
    Late
    -0.32
     in
    -0.32
    POSITIVE LOGITS
    nip
    0.27
    è¡Į人
    0.27
    åIJĽåŃIJ
    0.26
    è·ĸ
    0.25
    enge
    0.24
    èIJĿ
    0.24
    åīĬ
    0.24
    _EXECUTE
    0.23
    éĺµ
    0.23
    oren
    0.23
    Activations Density 0.787%

    No Known Activations