© 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. 9-TRANSCODER-HP
    7. 29397
    Prev
    Next
    INDEX
    Explanations

    lip

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_9.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.9.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    åѦåĪ°
    -0.26
    éĥ½
    -0.26
    lide
    -0.25
    issan
    -0.25
    riter
    -0.25
    æĸ°éĻĪ
    -0.25
    awan
    -0.24
    éĥ½å¾Ī
    -0.24
     such
    -0.23
     Collision
    -0.23
    POSITIVE LOGITS
    abeth
    0.27
    aterangepicker
    0.26
    agate
    0.25
    洪水
    0.25
    Ware
    0.24
    æѤæĸĩ
    0.24
     =",
    0.23
    楮
    0.23
    ahas
    0.23
    =-=-=-=-=-=-=-=-
    0.23
    Activations Density 2.328%

    No Known Activations