© 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. 54573
    Prev
    Next
    INDEX
    Explanations

    a / an

    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
    mouth
    -0.37
    æĦŁæŁĵèĢħ
    -0.30
    oine
    -0.30
    -mouth
    -0.27
    ppe
    -0.27
    åı£æ°Ķ
    -0.26
    ManagerInterface
    -0.26
    OMPI
    -0.25
     ballots
    -0.25
    taire
    -0.25
    POSITIVE LOGITS
    Âł
    0.32
    ç©·
    0.30
    çĶŁåŃĺ
    0.30
     lost
    0.29
    PO
    0.28
     real
    0.28
    窮
    0.27
     cas
    0.26
    aus
    0.26
     R
    0.26
    Activations Density 0.108%

    No Known Activations