© 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. 52598
    Prev
    Next
    INDEX
    Explanations

    ph

    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
     perch
    -0.29
    yers
    -0.28
    PAR
    -0.27
    quarters
    -0.27
    çĺ«
    -0.26
    å±ģèĤ¡
    -0.26
    icient
    -0.26
     paralysis
    -0.26
    YN
    -0.26
     nu
    -0.25
    POSITIVE LOGITS
    ç«ŀäºī
    0.28
    elp
    0.28
    溯
    0.28
    _eps
    0.26
    nea
    0.26
    转
    0.26
    .setLevel
    0.26
    scoped
    0.25
    声
    0.25
    æķ¬
    0.25
    Activations Density 0.012%

    No Known Activations