© 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. 19942
    Prev
    Next
    INDEX
    Explanations

    rapid/fast developments

    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
    èĮ¹
    -0.10
    наÑĤ
    -0.09
    çī¹æĦı
    -0.09
    Extend
    -0.09
    ç»ĵæĿŁ
    -0.09
    æѧ
    -0.09
    gregated
    -0.09
    croft
    -0.08
    umin
    -0.08
    å¤ļ人
    -0.08
    POSITIVE LOGITS
    å¿«éĢŁåıijå±ķ
    0.17
     rapid
    0.16
     rapidly
    0.16
    rapid
    0.15
    å¿«éĢŁ
    0.15
    è¿ħéĢŁ
    0.15
     Rapid
    0.14
    è¾ĥå¿«
    0.14
    è¿ħçĮĽ
    0.14
    å¿«éĢŁå¢ŀéķ¿
    0.13
    Activations Density 0.118%

    No Known Activations