© 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. 23189
    Prev
    Next
    INDEX
    Explanations

    Code, medical, and legal snippets

    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
     Gibraltar
    -0.27
     arc
    -0.27
    为ä¸Ģä½ĵ
    -0.26
    çĶŁæĢķ
    -0.26
    arc
    -0.25
     Prest
    -0.24
    太è¿ĩ
    -0.24
     vacc
    -0.24
     League
    -0.24
    åŃĺåľ¨ä¸Ģå®ļ
    -0.24
    POSITIVE LOGITS
    rent
    0.34
     kitty
    0.28
    ognito
    0.25
    éĢĤåºĶ
    0.24
    AGE
    0.24
     baÄŁlant
    0.24
     ìĹ
    0.23
     Morg
    0.23
    %C
    0.23
    EB
    0.23
    Activations Density 0.001%

    No Known Activations