© 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. 54553
    Prev
    Next
    INDEX
    Explanations

    names

    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
    bil
    -0.28
    pl
    -0.26
    nde
    -0.25
    Pl
    -0.24
    nd
    -0.24
    les
    -0.24
    rdf
    -0.24
    .ro
    -0.23
    tuple
    -0.23
    å§Ķåijĺ
    -0.23
    POSITIVE LOGITS
    iram
    0.29
    çIJ¥
    0.29
    acob
    0.29
    对åŃ©åŃIJ
    0.27
    Indicator
    0.25
    _indicator
    0.25
    å°ıçĭĹ
    0.25
    åħ±éĿĴ
    0.25
    ."+
    0.25
    æĹ¥åŃIJ
    0.25
    Activations Density 0.005%

    No Known Activations