© 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. 96263
    Prev
    Next
    INDEX
    Explanations

    code/technical language

    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
     other
    -0.28
     Pos
    -0.26
    amon
    -0.26
    (Pos
    -0.25
    ĪæĿĥ
    -0.25
    pyx
    -0.25
    线ä¸ĭ
    -0.25
     tf
    -0.24
    ynes
    -0.23
    åħ¶ä»ĸ
    -0.23
    POSITIVE LOGITS
    çIJĨ解åĴĮ
    0.28
     semester
    0.27
    åĵªä¸Ģ个
    0.26
     Markup
    0.26
    nature
    0.25
    æĢ§åĴĮ
    0.25
     authorised
    0.24
     Meaning
    0.24
    æľį
    0.24
    /display
    0.24
    Activations Density 0.001%

    No Known Activations