© 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. 27-TRANSCODER-HP
    7. 8943
    Prev
    Next
    INDEX
    Explanations

    equal to

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_27.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.27.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    cade
    -0.33
    ç¥Ŀç¦ı
    -0.25
    rig
    -0.25
    ç«Ļç«ĭ
    -0.24
    worker
    -0.24
    zel
    -0.24
    -supported
    -0.24
    èŀŃ
    -0.24
    æ´»åĬ¨çİ°åľº
    -0.24
    .prot
    -0.23
    POSITIVE LOGITS
     the
    0.31
     os
    0.29
    nar
    0.27
    çĶļä¹Ī
    0.26
     Pron
    0.26
     rew
    0.26
    [code
    0.26
    q
    0.26
     Tre
    0.25
     $$
    0.25
    Activations Density 0.007%

    No Known Activations