© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 19731
    Prev
    Next
    INDEX
    Explanations

    fingers and finger-related phrases

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    adamkarvonen/qwen3-32b-saes/saes_Qwen_Qwen3-32B_batch_top_k/resid_post_layer_32
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    OSH
    -0.09
    ervoir
    -0.09
    sic
    -0.09
    _vi
    -0.09
    anax
    -0.09
     lÆ°ng
    -0.09
    راب
    -0.08
    ologue
    -0.08
    èĽ©
    -0.08
    sess
    -0.08
    POSITIVE LOGITS
    /thumb
    0.15
    hole
    0.10
    ering
    0.10
    cake
    0.09
    нал
    0.09
    holes
    0.09
    æı®
    0.09
    鸳
    0.09
    essen
    0.08
    ULAR
    0.08
    Activations Density 0.018%

    No Known Activations