© 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. 12-TRANSCODER-HP
    7. 22488
    Prev
    Next
    INDEX
    Explanations

    adaptive

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_12.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.12.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    åĨľå®¶
    -0.26
    èijĨ
    -0.26
    iola
    -0.26
    ehler
    -0.25
     youngest
    -0.25
    èĪ¹ä¸Ĭ
    -0.24
    åİŁä»¶
    -0.24
    è¿Ļè¾ĪåŃIJ
    -0.24
    ellas
    -0.24
    è´£ç¼ĸ
    -0.23
    POSITIVE LOGITS
    éģ¥
    0.28
    iped
    0.27
    say
    0.26
    污æŁĵ
    0.25
    è¿ľ
    0.25
     Stick
    0.25
     grate
    0.25
     requestOptions
    0.25
    Season
    0.25
    ç²ĺ
    0.25
    Activations Density 0.001%

    No Known Activations