© 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. 62437
    Prev
    Next
    INDEX
    Explanations

    2- substituted compounds

    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
    ç¦ģ
    -0.10
    æĥ°
    -0.09
    .Inject
    -0.09
    çĶ°
    -0.09
    åĨ»ç»ĵ
    -0.08
    å¶Ĥ
    -0.08
     Eig
    -0.08
    çĹħæ¯ĴæĦŁæŁĵ
    -0.08
    áĥļ
    -0.08
     Westbrook
    -0.08
    POSITIVE LOGITS
    argin
    0.09
    ä¿¡å¿ĥ
    0.09
    çļĦæĥħ绪
    0.09
    没æľīæĥ³åĪ°
    0.09
    åŃij
    0.08
    å·¥ä½ľæĬ¥åijĬ
    0.08
    _CONFIG
    0.08
    æĥ³ä¸įåĪ°
    0.08
    å¼ĢéŨ
    0.08
    ysis
    0.08
    Activations Density 0.423%

    No Known Activations