© 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. 50733
    Prev
    Next
    INDEX
    Explanations

    list, version, link, copy, timeline

    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
    è¿Ļæł·ä¸Ģ
    -0.11
    çĶŁæ°Ķ
    -0.09
    ä¸ĭæīĭ
    -0.09
    尾巴
    -0.09
    好å¥ĩå¿ĥ
    -0.09
    æ·Ħ
    -0.09
    ÑģÑĤа
    -0.09
    åħļ
    -0.09
    èĹģ
    -0.09
    rape
    -0.08
    POSITIVE LOGITS
    .currentTime
    0.09
    æŃ¤é¡¹
    0.08
    å®Ĺ
    0.08
    该项
    0.08
    exus
    0.08
    éĢģæĿ¥
    0.08
    å½±
    0.08
     наÑĪего
    0.08
    åĬ
    0.08
    èĢģ家
    0.08
    Activations Density 0.157%

    No Known Activations