© 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. 33-TRANSCODER-HP
    7. 52523
    Prev
    Next
    INDEX
    Explanations

    say "House" word

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_33.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.33.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Negative Logits
    _UNIQUE
    -0.27
    idel
    -0.27
    ç§ijæĬĢè¿ĽæŃ¥
    -0.26
    :host
    -0.26
     originals
    -0.26
    inan
    -0.26
    udoku
    -0.25
    yz
    -0.25
     mobility
    -0.25
     ages
    -0.24
    POSITIVE LOGITS
    æ·±
    0.29
     Deep
    0.26
    æ¡Ģ
    0.25
    éĶŃ
    0.25
    stance
    0.24
    éĶĢåĶ®æĶ¶åħ¥
    0.23
    igate
    0.23
    æ·±å¤Ħ
    0.23
    cest
    0.23
    Deep
    0.23
    Activations Density 0.020%

    No Known Activations