© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-4B
    5. 12-TRANSCODER-HP
    7. 24177
    Prev
    Next
    INDEX
    Explanations

    CRISPR

    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
    Negative Logits
    SetName
    -0.27
    uden
    -0.26
    å¥Ĥ
    -0.26
    éĽ·è¾¾
    -0.25
    ObjectName
    -0.25
    lesi
    -0.25
     Debugger
    -0.25
    -expanded
    -0.24
    KIT
    -0.24
    ilated
    -0.24
    POSITIVE LOGITS
    thal
    0.31
    editable
    0.27
    ":-
    0.27
    éħ¥
    0.27
    bridge
    0.26
    Cancelable
    0.26
     INCLUDED
    0.26
    æ¡¥
    0.25
    NoSuch
    0.25
    IDGE
    0.24
    Activations Density 0.003%

    No Known Activations