© 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. 54834
    Prev
    Next
    INDEX
    Explanations

    ie

    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
     pp
    -0.28
     pins
    -0.26
    /pp
    -0.25
    herent
    -0.25
    æģ©
    -0.25
    ä¸Ī夫
    -0.25
    è¤IJ
    -0.24
    verbs
    -0.24
     husband
    -0.24
     pin
    -0.24
    POSITIVE LOGITS
    prim
    0.32
    ioni
    0.30
    zes
    0.28
    lds
    0.26
    lfw
    0.26
    zá
    0.25
    ft
    0.24
    finder
    0.24
    imps
    0.24
    èĩªçĦ¶èĢĮ
    0.24
    Activations Density 0.018%

    No Known Activations