© 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. 23459
    Prev
    Next
    INDEX
    Explanations

    story, movie, or book plots

    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
    _VC
    -0.10
     VC
    -0.08
    æĽ¾ç¶ĵ
    -0.08
    èĩªä¿¡
    -0.08
    说è¿ĩ
    -0.08
    èĩªå¾ĭ
    -0.08
    ÙĦØŃ
    -0.08
    ÑĢабоÑĤка
    -0.08
     Barg
    -0.08
    ÑģÑĤой
    -0.08
    POSITIVE LOGITS
    为主线
    0.12
    å±ķå¼Ģ
    0.12
    串èģĶ
    0.11
    æĭľå¸ĪåѦèīº
    0.10
    äºĨä¸Ģç³»åĪĹ
    0.09
    æ¸İ
    0.09
    ä¸Ģå¹ķ
    0.09
    åºıå¹ķ
    0.09
    roulette
    0.09
    交代
    0.09
    Activations Density 0.090%

    No Known Activations