© 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. 11050
    Prev
    Next
    INDEX
    Explanations

    take in / take an / take some

    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
     shadow
    -0.09
    laps
    -0.08
    è°
    -0.08
     fret
    -0.08
    _shadow
    -0.08
    èĢ½
    -0.08
    ucher
    -0.08
    åĬŁè¯¾
    -0.08
    为æŃ¢
    -0.08
    uper
    -0.08
    POSITIVE LOGITS
    çİ°æľīçļĦ
    0.11
    åİŁæľīçļĦ
    0.10
    åľ¨è¿ĩåİ»
    0.10
    å¹³æŶ
    0.10
    è¿ĩåİ»çļĦ
    0.10
    å¾Ī大
    0.09
     اÙĦÙĥÙĦ
    0.09
    UTO
    0.09
    并å°Ĩ
    0.09
    çĻ¾ä½Ļ
    0.09
    Activations Density 0.140%

    No Known Activations