© 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. 20-TRANSCODER-HP
    7. 141757
    Prev
    Next
    INDEX
    Explanations

    on

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_20.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.20.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    è¿Ļåıª
    -0.34
    éĤ£åıª
    -0.29
     franca
    -0.28
    è¿Ļä½į
    -0.27
    ä¸İåıijå±ķ
    -0.26
    两åıª
    -0.26
    istor
    -0.26
     {*}
    -0.24
    没æĶ¶
    -0.24
    -var
    -0.24
    POSITIVE LOGITS
     smart
    0.26
     legitimate
    0.26
    Ĥ¬
    0.26
    veau
    0.24
     reliable
    0.24
     complete
    0.24
    complete
    0.24
     oc
    0.24
     machine
    0.24
     rect
    0.24
    Activations Density 23.871%

    No Known Activations