© 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. 19-TRANSCODER-HP
    7. 8502
    Prev
    Next
    INDEX
    Explanations

    Ovaries/ovulation

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_19.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.19.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    anners
    -0.26
    泯
    -0.25
    åĽŀäºĭ
    -0.24
     Authorities
    -0.24
    anything
    -0.24
    postData
    -0.24
    å½¼
    -0.23
    çļĦä¼Łå¤§
    -0.23
    ANNER
    -0.23
    ysters
    -0.23
    POSITIVE LOGITS
    æł¸å®ļ
    0.27
    é«ĺå³°æľŁ
    0.25
    elles
    0.25
    ieres
    0.24
    emarks
    0.24
     cr
    0.23
     USING
    0.23
    noc
    0.23
    Holder
    0.23
    oly
    0.23
    Activations Density 0.079%

    No Known Activations