© 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. 37413
    Prev
    Next
    INDEX
    Explanations

    container of items

    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
    æ¯Ķè¾ĥ大
    -0.09
     oe
    -0.09
    è¢ĭåŃIJ
    -0.09
    uida
    -0.08
    åĭº
    -0.08
    åıijå±ķéĺ¶æ®µ
    -0.08
    åĬ¨çī©åĽŃ
    -0.08
    ufe
    -0.08
    _Framework
    -0.08
    æ¯Ķè¾ĥå¤ļ
    -0.08
    POSITIVE LOGITS
    诣
    0.10
    ç®Ń
    0.09
    hall
    0.09
    entially
    0.09
    ÑĦÑĦ
    0.08
    rax
    0.08
    ht
    0.08
    è°ĥéħį
    0.08
    满满çļĦ
    0.08
    rase
    0.08
    Activations Density 0.018%

    No Known Activations