© 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. 53585
    Prev
    Next
    INDEX
    Explanations

    reflexive pronouns

    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
    åħ«å¤§
    -0.09
    åģļçļĦäºĭæĥħ
    -0.09
    èĢĮæĪIJ
    -0.08
    æĪij们éĥ½
    -0.08
    ä¸Ģæĸ¹éĿ¢æĺ¯
    -0.08
    åĨįåĬłä¸Ĭ
    -0.08
    éģ¥
    -0.08
    èĶ½
    -0.08
     haystack
    -0.08
    avage
    -0.08
    POSITIVE LOGITS
    ç»ıåİĨ
    0.09
    _gps
    0.09
    æī¶
    0.09
    è¯ķéªĮ
    0.09
    ç»ıçIJĨ
    0.09
    ç»ıåİĨäºĨ
    0.09
    èĩ»
    0.09
    被åĪ¤
    0.09
    çģ«çĥŃ
    0.09
    .dsl
    0.08
    Activations Density 0.023%

    No Known Activations