© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 29715
    Prev
    Next
    INDEX
    Explanations

    litter contexts: littering, retrieving, littered, deposits, mates, carry

    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
    gettext
    -0.09
    éĤ¸
    -0.08
    _tunnel
    -0.08
    san
    -0.08
    صÙĪÙĦ
    -0.08
    aze
    -0.08
    ðŁı»
    -0.08
     sheer
    -0.08
    è¦ģæĬĬ
    -0.08
    åĶĶ
    -0.08
    POSITIVE LOGITS
    edException
    0.13
    è¢ĭ
    0.10
    ç¬Ĩ
    0.10
    plet
    0.09
    PILE
    0.09
    å¼ĢæĿ¥
    0.09
    èĽĽ
    0.09
    è¤Ĵ
    0.09
    çĦ¶æĺ¯
    0.09
    coins
    0.09
    Activations Density 0.003%

    No Known Activations