© 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. 96519
    Prev
    Next
    INDEX
    Explanations

    Code/technical text

    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
    å®Į
    -0.27
    elow
    -0.27
    转åIJij
    -0.26
    ениÑİ
    -0.26
    åĬŀçIJĨ
    -0.26
    æŀļ
    -0.26
    夺åıĸ
    -0.26
     attainment
    -0.26
    äºīåĪĽ
    -0.26
    elter
    -0.24
    POSITIVE LOGITS
    berries
    0.26
     '~/
    0.24
     jane
    0.24
    /ay
    0.24
     SIDE
    0.23
    formats
    0.23
    osex
    0.23
    зван
    0.23
    umbing
    0.23
    çĶŁçī©åѦ
    0.23
    Activations Density 0.004%

    No Known Activations