© 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. 12-TRANSCODER-HP
    7. 23828
    Prev
    Next
    INDEX
    Explanations

    clean

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_12.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.12.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ears
    -0.35
    å®Į
    -0.31
    airo
    -0.27
    ennie
    -0.27
    å®Įæķ´
    -0.27
    åŁ
    -0.26
    pm
    -0.26
    å®Įç¾İ
    -0.25
    ibir
    -0.25
    apers
    -0.25
    POSITIVE LOGITS
     outr
    0.28
     cá
    0.26
    åħ±çĶŁ
    0.25
    å©¿
    0.24
     OnePlus
    0.24
     Dodge
    0.24
    æĹħ游度åģĩ
    0.24
    Ỷ
    0.24
    裹
    0.24
    è¡Įä¸ļåįıä¼ļ
    0.24
    Activations Density 0.005%

    No Known Activations