© 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. 31-TRANSCODER-HP
    7. 18695
    Prev
    Next
    INDEX
    Explanations

    clinical studies

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_31.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.31.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    笼
    -0.28
    ug
    -0.28
    æī¾
    -0.27
     finds
    -0.27
    å¤įåħ´
    -0.26
    ç¨Ģ缺
    -0.26
    è´´
    -0.26
     Gardens
    -0.26
    /setup
    -0.26
    æŁ±
    -0.25
    POSITIVE LOGITS
    çłĶ究
    0.31
    åıĮåIJij
    0.28
    ruise
    0.27
    embros
    0.27
    åĬĽè¿ĺæĺ¯
    0.26
    ä¸įå°½
    0.26
    ìĹ°êµ¬
    0.25
    ophe
    0.25
    çłĶ讨
    0.25
    çłĶ
    0.24
    Activations Density 0.239%

    No Known Activations