© 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. 52743
    Prev
    Next
    INDEX
    Explanations

    Historical contexts

    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
    [assembly
    -0.28
     бÑİ
    -0.26
    iciente
    -0.25
    apus
    -0.25
    ertos
    -0.25
    (QL
    -0.25
     Covered
    -0.25
    boost
    -0.25
    zar
    -0.25
    ento
    -0.25
    POSITIVE LOGITS
    ä¹³
    0.33
    em
    0.33
    _EM
    0.30
    使人
    0.30
     em
    0.28
    çĥĪ
    0.28
    'em
    0.28
    anders
    0.27
     Em
    0.26
     leg
    0.26
    Activations Density 0.018%

    No Known Activations