© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 9664
    Prev
    Next
    INDEX
    Explanations

    oxide dismutase

    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
    èīºæľ¯åĵģ
    -0.09
    åĪĴåĪĨ
    -0.08
     dere
    -0.08
    ä¸įæŃ»
    -0.08
    æݥ轨
    -0.08
    èĢ½
    -0.08
    multipart
    -0.08
    æĹ©å°±
    -0.08
    èĬ±æł·
    -0.08
     Hind
    -0.07
    POSITIVE LOGITS
    å½Ŀ
    0.10
    çİĭæĻĵ
    0.10
    ây
    0.10
    UB
    0.09
    éĹ®ä»ĸ
    0.09
    zell
    0.09
    åķ¡
    0.09
    ç´¯äºĨ
    0.09
    éĥĹ
    0.09
    ellas
    0.09
    Activations Density 0.224%

    No Known Activations