© 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. 54639
    Prev
    Next
    INDEX
    Explanations

    bodies

    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
    æģ¯
    -0.31
    ä¾Ķ
    -0.27
    tems
    -0.25
    æĤŁ
    -0.25
    ivism
    -0.25
    SCO
    -0.25
    ikal
    -0.25
    åİŁæłĩé¢ĺ
    -0.24
    æĭĽèĤ¡
    -0.24
    åŃ©
    -0.24
    POSITIVE LOGITS
    loff
    0.27
    ost
    0.27
    yet
    0.26
     voice
    0.26
    VERBOSE
    0.25
     fir
    0.25
     pir
    0.25
     studs
    0.25
    åįħ
    0.25
    ston
    0.25
    Activations Density 0.010%

    No Known Activations