© 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. 33-TRANSCODER-HP
    7. 53168
    Prev
    Next
    INDEX
    Explanations

    ovarian cancer

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_33.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.33.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    大ä¼Ĺ
    -0.29
    olen
    -0.29
    amo
    -0.28
    éĺ¿
    -0.26
     pe
    -0.25
     vuel
    -0.25
     Gold
    -0.25
    çļĦéĩįçĤ¹
    -0.25
    ane
    -0.25
    loh
    -0.25
    POSITIVE LOGITS
    åijĬè¯ī她
    0.29
     Cbd
    0.29
    ipop
    0.27
    pei
    0.26
    "..
    0.25
    ,âĢ¦↵↵
    0.25
    dea
    0.25
    setTitle
    0.25
    大å¦Ī
    0.25
    zyst
    0.25
    Activations Density 0.009%

    No Known Activations