© 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. 23-TRANSCODER-HP
    7. 24360
    Prev
    Next
    INDEX
    Explanations

    -in

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_23.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.23.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Eug
    -0.25
    oin
    -0.24
     todo
    -0.24
    ÑĶ
    -0.24
    ien
    -0.24
     themselves
    -0.24
     myself
    -0.23
    åıĬåħ¶ä»ĸ
    -0.23
    عÙĬ
    -0.23
     Ob
    -0.23
    POSITIVE LOGITS
     Walsh
    0.29
    ueue
    0.27
     hauling
    0.25
    è¿ĺåı¯
    0.24
    ä»Ģä¹Īåij¢
    0.24
    ä¸Ĭ游
    0.24
    æĬ¥åijĬæĺ¾ç¤º
    0.23
    .reporting
    0.23
    -caret
    0.23
     cudd
    0.23
    Activations Density 0.018%

    No Known Activations