© 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. 4928
    Prev
    Next
    INDEX
    Explanations

    X-Men, mutant, evolved, ants

    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
    èĦ±
    -0.11
     اÙĦÙĥÙĦ
    -0.09
    åı¤éķĩ
    -0.09
    头
    -0.09
    éĤ£åıª
    -0.09
     TOD
    -0.09
    anker
    -0.09
    æµģè¡Į
    -0.08
    åĽłåľ°åĪ¶å®ľ
    -0.08
    sono
    -0.08
    POSITIVE LOGITS
    诮
    0.11
    åıĺæĢģ
    0.10
    天èµĭ
    0.10
    èŃ°
    0.09
    åıĺå½¢
    0.09
    è§īéĨĴ
    0.09
     talent
    0.08
    ahren
    0.08
    çĶŁçī©ç§ijæĬĢ
    0.08
    å¹³æķ´
    0.08
    Activations Density 0.067%

    No Known Activations