© 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. 95882
    Prev
    Next
    INDEX
    Explanations

    eyes and vision

    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
    reserve
    -0.29
    åĤ¨å¤ĩ
    -0.29
    æķĻ
    -0.28
     reserve
    -0.26
     reserv
    -0.26
     reserves
    -0.25
    -pad
    -0.25
    éĢĢç¨İ
    -0.25
    ä»»åĬ¡
    -0.24
    .oracle
    -0.24
    POSITIVE LOGITS
     libr
    0.30
     Chart
    0.29
    -testing
    0.29
    -chart
    0.29
     chart
    0.28
    osite
    0.26
    Chart
    0.26
     lib
    0.25
    .rs
    0.25
     testing
    0.25
    Activations Density 0.007%

    No Known Activations