© 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. 37481
    Prev
    Next
    INDEX
    Explanations

    cue or cues

    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
    éĴ¥
    -0.09
    bjerg
    -0.09
    shire
    -0.09
    cour
    -0.09
    ãģªãĤĬ
    -0.09
    okin
    -0.08
    èıģ
    -0.08
    éĻIJ度
    -0.08
    ниÑĩ
    -0.08
    pig
    -0.08
    POSITIVE LOGITS
    eer
    0.10
    ytt
    0.10
    举æŃ¢
    0.10
    åĬ¬
    0.09
    ement
    0.09
    edList
    0.08
    ä»Ĺ
    0.08
    æ³ķå¾ĭ顾éĹ®
    0.08
    åįģ足
    0.08
    åŃļ
    0.08
    Activations Density 0.006%

    No Known Activations