© 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. 34405
    Prev
    Next
    INDEX
    Explanations

    phylogenetic relationships and species classification

    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
    ä¾ĽçĶµ
    -0.11
    涯
    -0.09
    宣
    -0.09
    ç±į
    -0.09
    åŁİå¸Ĥ建设
    -0.08
    озв
    -0.08
    å°ī
    -0.08
    >Main
    -0.08
    æİ¥çĿĢ
    -0.08
    HIR
    -0.08
    POSITIVE LOGITS
    åħ³ç³»
    0.13
    亲
    0.11
    亲è¿ij
    0.10
    å²IJ
    0.10
     relationship
    0.09
    親
    0.09
    ä¸Ģ段æŶéĹ´
    0.09
    亲åĪĩ
    0.09
    çļĦåħ³ç³»
    0.09
    è°Ĭ
    0.09
    Activations Density 0.090%

    No Known Activations