© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-4B
    5. 30-TRANSCODER-HP
    7. 96003
    Prev
    Next
    INDEX
    Explanations

    News reports / articles

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_30.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.30.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     hoops
    -0.29
     każdy
    -0.25
    æݥ轨
    -0.25
     packs
    -0.24
     contemplated
    -0.24
    posal
    -0.24
     dÅĤ
    -0.24
    $core
    -0.24
    ernes
    -0.24
     dipping
    -0.23
    POSITIVE LOGITS
    after
    0.39
    åIJİ
    0.36
    .after
    0.36
     after
    0.34
    _after
    0.32
    âĢ¦..
    0.31
    åIJİçļĦ
    0.31
    After
    0.31
    âĢ¦.
    0.30
    âĢ¦the
    0.30
    Activations Density 0.904%

    No Known Activations