© 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. 96501
    Prev
    Next
    INDEX
    Explanations

    computer code and 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
    çĶŁçī©
    -0.31
     biod
    -0.31
    æĭŁ
    -0.29
    åĪ¶
    -0.28
     biological
    -0.26
     frame
    -0.26
     Bij
    -0.25
     bij
    -0.25
     leven
    -0.25
    æķ¬
    -0.25
    POSITIVE LOGITS
    arios
    0.28
     Quiet
    0.26
     bree
    0.25
    Eye
    0.25
    .provider
    0.25
    æ·±åĪĩ
    0.24
    uples
    0.24
    æ½ĩæ´Ĵ
    0.24
    editor
    0.24
    gee
    0.23
    Activations Density 0.882%

    No Known Activations