© 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. 141270
    Prev
    Next
    INDEX
    Explanations

    Organizations and formal proceedings

    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
     Abrams
    -0.27
    ombok
    -0.25
    OMET
    -0.25
     sack
    -0.25
     susp
    -0.25
    aus
    -0.25
     declining
    -0.24
    è¿IJè¾ĵ
    -0.24
    èĤ¡
    -0.24
    ç´Ģ
    -0.24
    POSITIVE LOGITS
    nic
    0.29
     Suff
    0.29
    pra
    0.26
    ori
    0.25
    åıĸæ¶Ī
    0.24
     Past
    0.24
    å°ıç¼ĸä¸Ģèµ·
    0.24
    æį¢åıĸ
    0.24
    æľĢæĸ°
    0.23
    ["$
    0.23
    Activations Density 22.206%

    No Known Activations