© 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. 25065
    Prev
    Next
    INDEX
    Explanations

    еÑģÑĤÑĮ

    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
    æĺ¯ä¸ª
    -0.28
     maç
    -0.27
    æ»´
    -0.27
    either
    -0.27
    çļĦæľºä¼ļ
    -0.26
    comp
    -0.26
    ombo
    -0.26
    è¦ģä¹Ī
    -0.26
    elan
    -0.26
     either
    -0.26
    POSITIVE LOGITS
    åŃĺåľ¨çĿĢ
    0.42
    è¿ĺæľīå¾Īå¤ļ
    0.40
    è¿ĺæľī
    0.40
    è¿ĺæľīä¸ĢäºĽ
    0.39
     exists
    0.38
     existence
    0.36
    éĤĦæľī
    0.36
     existed
    0.35
     there
    0.35
    Exists
    0.33
    Activations Density 0.001%

    No Known Activations