© 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. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 61739
    Prev
    Next
    INDEX
    Explanations

    storytelling

    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
    è½»
    -0.10
    æĪij对
    -0.09
    .keep
    -0.09
    æĢİä¹Īçľĭ
    -0.09
    ãĥ¥ãĥ¼
    -0.08
    ASI
    -0.08
    éĢģç»Ļ
    -0.08
    تÙĩا
    -0.08
    çŁ¥åIJį
    -0.08
     Mens
    -0.08
    POSITIVE LOGITS
     storytelling
    0.10
    åıĻ
    0.09
    ä¼IJ
    0.09
    èĤ²
    0.09
    PED
    0.09
    弧
    0.09
    æķħäºĭ
    0.08
     stories
    0.08
     Dudley
    0.08
    åĩºæīĭ
    0.08
    Activations Density 0.041%

    No Known Activations