© 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. 19739
    Prev
    Next
    INDEX
    Explanations

    this followed by noun

    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
    ü
    -0.09
    BN
    -0.09
    orem
    -0.09
    åĽłä¸ºåľ¨
    -0.08
    è±¹
    -0.08
    éĤĤ
    -0.08
    _UNUSED
    -0.08
    =rand
    -0.08
    èij©
    -0.08
    身边
    -0.08
    POSITIVE LOGITS
    çĨ¨
    0.10
    ustr
    0.09
    交ä¼ļ
    0.09
    erule
    0.09
    è¿Ļè¾ĪåŃIJ
    0.09
    è¶ĬæĿ¥
    0.09
    ickers
    0.09
    çĶ
    0.09
    å¼Ģæ°´
    0.09
    å§ĭç»ĪåĿļæĮģ
    0.09
    Activations Density 0.059%

    No Known Activations