© 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. 64447
    Prev
    Next
    INDEX
    Explanations

    Questions

    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
     $__
    -0.29
    éĢı
    -0.29
    .includes
    -0.27
    yla
    -0.26
     ver
    -0.26
    çľĭå¾ħ
    -0.25
    éĢļ
    -0.24
    avers
    -0.24
    åĮħåIJ«äºĨ
    -0.24
    .indexOf
    -0.24
    POSITIVE LOGITS
    elle
    0.27
    ikel
    0.27
     recoil
    0.25
    棣
    0.24
    èģĶ社
    0.24
     Egg
    0.23
     grac
    0.23
     exercising
    0.23
    eware
    0.23
    rc
    0.22
    Activations Density 0.208%

    No Known Activations