© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 8903
    Prev
    Next
    INDEX
    Explanations

    past traditions and nostalgia

    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
    ç»ĨåĪĻ
    -0.10
    åĪ
    -0.09
    æİĴè¡Į
    -0.08
    å¸Ń
    -0.08
    æŃĥ
    -0.08
    ä¼ĬåĪ©
    -0.08
    侵害
    -0.08
    ango
    -0.08
     dsp
    -0.07
    åľ¨ä¸ŃåĽ½
    -0.07
    POSITIVE LOGITS
    æŧ
    0.14
    èĪĬ
    0.13
    å¤įåı¤
    0.13
     old
    0.12
    èĢģæŧ
    0.12
     ÑģÑĤаÑĢ
    0.12
    -old
    0.12
     Old
    0.12
    backward
    0.12
    åİĨåı²
    0.12
    Activations Density 0.145%

    No Known Activations