© 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. 18525
    Prev
    Next
    INDEX
    Explanations

    difficulties and progress

    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
    æľĪæľ«
    -0.08
    çļĦæĥħå½¢
    -0.08
    æĪIJåĵģ
    -0.08
    reme
    -0.08
    趣
    -0.08
    èĩªæľī
    -0.08
    retty
    -0.08
     Record
    -0.07
    æĹłå¿§
    -0.07
    æĻ¨
    -0.07
    POSITIVE LOGITS
    éĨĴ
    0.13
    åIJĪåĬĽ
    0.11
    æĪij们å¿ħé¡»
    0.11
    è§īéĨĴ
    0.11
    æĤ²è§Ĥ
    0.10
    avern
    0.10
    æĪij们éľĢè¦ģ
    0.10
    можем
    0.10
    å¦ĤæŀľæĪij们
    0.10
    åı·åı¬
    0.10
    Activations Density 0.090%

    No Known Activations