© 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. 37623
    Prev
    Next
    INDEX
    Explanations

    dispersion medium or injection into

    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
    ä»ĸ们çļĦ
    -0.09
    éĴĿ
    -0.09
     their
    -0.09
    their
    -0.08
    åºķèķ´
    -0.08
     themselves
    -0.08
    对åħ¶
    -0.08
     Affero
    -0.08
    å®ĥ们
    -0.08
    edic
    -0.08
    POSITIVE LOGITS
    æijĬ
    0.11
    éĢłåŀĭ
    0.09
    åĩī
    0.09
    å¯ĴåĨ¬
    0.09
    asan
    0.09
    tram
    0.09
    мол
    0.08
    å¯Ĵ
    0.08
    erais
    0.08
    slides
    0.08
    Activations Density 0.041%

    No Known Activations