© 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. 23139
    Prev
    Next
    INDEX
    Explanations

    launch

    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
    åĬŀåħ¬åİħ
    -0.27
    inn
    -0.26
     Nä
    -0.25
    æĦıåĽ¾
    -0.24
    éĺ´
    -0.24
    ç§ĺ书éķ¿
    -0.24
    ynn
    -0.24
     اÙĦÙĦ
    -0.24
    \Active
    -0.24
     xrange
    -0.23
    POSITIVE LOGITS
     haul
    0.28
    elson
    0.28
    æĸĩåĮĸ交æµģ
    0.27
    ainers
    0.26
    aska
    0.26
    opher
    0.25
     flavours
    0.25
     flavors
    0.25
    asco
    0.24
    ä¸ºä½ł
    0.24
    Activations Density 0.001%

    No Known Activations