© 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. 21949
    Prev
    Next
    INDEX
    Explanations

    shadow

    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
     ignored
    -0.28
    /avatar
    -0.27
    contri
    -0.26
    vid
    -0.26
    åĤ³éĢģ
    -0.25
     Viagra
    -0.25
     preservation
    -0.25
     absorbing
    -0.24
     condu
    -0.24
    æķ¦
    -0.24
    POSITIVE LOGITS
    tere
    0.29
    ppo
    0.29
    ufs
    0.28
     thÆ°á»Ľc
    0.27
    chemist
    0.26
    rome
    0.26
    agog
    0.24
    å½·
    0.24
    à¹Ħล
    0.24
    å°º
    0.23
    Activations Density 0.000%

    No Known Activations