© 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. 49048
    Prev
    Next
    INDEX
    Explanations

    work with others

    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
    äºĭå®ľ
    -0.10
    енÑĮ
    -0.10
    åĽłä¸ºåľ¨
    -0.09
    ä»Ģä¹Īäºĭ
    -0.09
    èľĤ
    -0.09
    è§Ĩå¯Ł
    -0.08
     Buckley
    -0.08
    éĸĴ
    -0.08
    å½ĵæĪij
    -0.08
    çĶŁäº§åĬĽ
    -0.08
    POSITIVE LOGITS
     thả
    0.09
    unte
    0.09
    redicate
    0.09
     Sov
    0.09
    åį«
    0.09
     Kes
    0.09
    æĪij们ä¸Ģèµ·
    0.08
    _known
    0.08
    åĪĢ
    0.08
    åģļä¸įåĪ°
    0.08
    Activations Density 0.034%

    No Known Activations