© 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. 1655
    Prev
    Next
    INDEX
    Explanations

    in alignment with

    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
     assertNotNull
    -0.09
    çģµæ´»
    -0.08
    ÄĻd
    -0.08
    _both
    -0.08
    UNUSED
    -0.08
    æĪIJè´¥
    -0.08
     Shiv
    -0.08
    imple
    -0.08
     Tear
    -0.08
    ç®Ģåįķ
    -0.08
    POSITIVE LOGITS
    符åIJĪ
    0.25
    å¥ijåIJĪ
    0.21
    åIJ»
    0.18
    è¿İåIJĪ
    0.17
    顺åºĶ
    0.16
    ä¸į符åIJĪ
    0.16
    缸符
    0.15
    æŃ£å¥½
    0.15
     align
    0.14
     phù
    0.14
    Activations Density 0.157%

    No Known Activations