© 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. 31-TRANSCODER-HP
    7. 18665
    Prev
    Next
    INDEX
    Explanations

    Jo

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_31.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.31.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ewe
    -0.27
    åħ¨æĻ¯
    -0.26
    orna
    -0.26
    /material
    -0.24
    transparent
    -0.24
    ç§ijåѦ
    -0.24
    apse
    -0.24
    iders
    -0.23
     bew
    -0.23
     drum
    -0.23
    POSITIVE LOGITS
    ä¸Ģ个éĹ®é¢ĺ
    0.28
    æĺ¥è¿IJ
    0.27
    ì¹Ń
    0.26
    äºĭæķħåıijçĶŁ
    0.25
     IOS
    0.24
    hap
    0.24
     ac
    0.23
     mj
    0.23
    hel
    0.23
     Andersen
    0.23
    Activations Density 0.156%

    No Known Activations