© 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. 11111
    Prev
    Next
    INDEX
    Explanations

    mitotic activity

    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
    活泼
    -0.12
    ä¸Ģè¾ĪåŃIJ
    -0.09
    æ¯ķ
    -0.09
    以人æ°ij
    -0.08
    ä¸Ģ线
    -0.08
    è¡Į人
    -0.08
     yield
    -0.08
    æ´»è·ĥ
    -0.08
    缸å½ĵ
    -0.08
     safe
    -0.08
    POSITIVE LOGITS
     Ñģли
    0.10
    çŃIJ
    0.10
    Elite
    0.10
    æ·«
    0.09
    æ³ķ人
    0.08
    obar
    0.08
    ucer
    0.08
    éĵĥ
    0.08
     Vil
    0.08
    ä½Ĺ
    0.08
    Activations Density 0.098%

    No Known Activations