© 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. 33-TRANSCODER-HP
    7. 54215
    Prev
    Next
    INDEX
    Explanations

    Technical/scientific texts

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_33.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.33.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     ground
    -1.06
     Ground
    -0.91
    ground
    -0.91
     eye
    -0.85
    Ground
    -0.85
    åľ°éĿ¢
    -0.79
    -ground
    -0.78
    eye
    -0.73
    _ground
    -0.73
     Eye
    -0.68
    POSITIVE LOGITS
    gil
    0.28
    _g
    0.27
     Gib
    0.26
     reorder
    0.26
     G
    0.26
    reon
    0.25
    bout
    0.25
    kest
    0.25
    gos
    0.25
    -g
    0.25
    Activations Density 0.127%

    No Known Activations