© 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. 21167
    Prev
    Next
    INDEX
    Explanations

    pop culture

    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
    é¦ĸåĪĽ
    -0.12
    ayo
    -0.10
    游客
    -0.10
    rv
    -0.09
    ç¥
    -0.09
    èµŃ
    -0.09
    emat
    -0.09
    \Html
    -0.09
    _BUSY
    -0.09
    PEC
    -0.09
    POSITIVE LOGITS
    ä¸Ģéĥ¨
    0.11
     movies
    0.11
     movie
    0.11
    æµģè¡Į
    0.10
    çĶµå½±
    0.10
     pop
    0.10
    串
    0.09
    å½±è§Ĩåī§
    0.09
     literature
    0.09
    ç»ıåħ¸
    0.09
    Activations Density 0.149%

    No Known Activations