© 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. 20-TRANSCODER-HP
    7. 63511
    Prev
    Next
    INDEX
    Explanations

    a, an

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_20.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.20.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    lus
    -0.31
    æĵħ
    -0.26
    ignal
    -0.26
    Prem
    -0.25
    ProcessEvent
    -0.25
    weep
    -0.24
     recre
    -0.24
    plib
    -0.24
    Ace
    -0.23
    lit
    -0.23
    POSITIVE LOGITS
     HAR
    0.29
    zÄħ
    0.28
    osi
    0.25
    è¯Ŀè¯ŃæĿĥ
    0.24
    ActionCreators
    0.24
    ä¼Ĭæĸ¯åħ°
    0.24
    äºĨä¸ĢäºĽ
    0.23
    顯
    0.23
    被æ·ĺæ±°
    0.23
    ahu
    0.23
    Activations Density 27.467%

    No Known Activations