© 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. 32-TRANSCODER-HP
    7. 43423
    Prev
    Next
    INDEX
    Explanations

    scientific and technical texts

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_32.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.32.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    èĥļèĥİ
    -0.26
    æ³Ĭ
    -0.26
    ä¸ĢåľĪ
    -0.26
    主è¦ģåİŁåĽł
    -0.25
     pane
    -0.25
    >Main
    -0.25
    æĪ´
    -0.25
    åŀĽ
    -0.24
     nood
    -0.24
    ç´§å¯Ĩ
    -0.24
    POSITIVE LOGITS
     whit
    0.28
    éľľ
    0.27
    èIJ½
    0.26
    utz
    0.24
    ARIABLE
    0.23
    èĬ¸
    0.23
    wh
    0.23
     haul
    0.23
    é£Ļ
    0.23
    ules
    0.23
    Activations Density 0.009%

    No Known Activations