© 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. 95414
    Prev
    Next
    INDEX
    Explanations

    9

    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
    cs
    -0.26
    luck
    -0.26
     verw
    -0.26
    æµĶ
    -0.25
    Inside
    -0.24
    bard
    -0.24
    _splits
    -0.24
     autonomy
    -0.24
    cratch
    -0.24
     fool
    -0.23
    POSITIVE LOGITS
    itty
    0.28
    ä»·æł¼ä¸Ĭ涨
    0.26
    odium
    0.25
    æĿ¥çĶµ
    0.25
    å®Ļ
    0.25
    reur
    0.25
    æĸĩåĮĸ建设
    0.25
    _lib
    0.25
     geom
    0.25
    omy
    0.24
    Activations Density 0.001%

    No Known Activations