© 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. 64261
    Prev
    Next
    INDEX
    Explanations

    Names

    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
    pecies
    -0.28
    ioxide
    -0.28
    åı£è¯Ń
    -0.27
    xED
    -0.26
    moth
    -0.25
     Plat
    -0.24
    走访
    -0.24
    ÙģØŃ
    -0.24
    -0.23
    (UI
    -0.23
    POSITIVE LOGITS
     Eventually
    0.26
    "d
    0.26
    tl
    0.26
    åī²
    0.24
    /*/
    0.24
    "<?
    0.24
    æĪij们å¿ħé¡»
    0.24
     Burke
    0.24
    ivol
    0.24
    ult
    0.24
    Activations Density 25.409%

    No Known Activations