© 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. 63081
    Prev
    Next
    INDEX
    Explanations

    God

    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
    çĶŁæ¶¯
    -0.27
    andler
    -0.25
    аÑĢÑĮ
    -0.25
    owie
    -0.24
     lifetime
    -0.24
    ÑĤиÑĢов
    -0.23
    anga
    -0.23
    讨
    -0.23
     limiting
    -0.23
    boost
    -0.23
    POSITIVE LOGITS
    yne
    0.28
    æĢı
    0.25
    è¾ĥå¿«
    0.24
    @a
    0.24
    etre
    0.24
    æĢĢçĸij
    0.24
    reo
    0.23
    çļĦ第ä¸Ģ个
    0.23
    ɸ
    0.23
     hesitate
    0.23
    Activations Density 20.217%

    No Known Activations