© 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. 27624
    Prev
    Next
    INDEX
    Explanations

    "Note: " or "NOTE:"

    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
    ä½Ĩå®ĥ
    -0.10
    asant
    -0.10
    çŃĶ辩
    -0.09
    owie
    -0.09
    intree
    -0.09
    áĥ©
    -0.09
    ÑĢен
    -0.09
    æ·ĩ
    -0.09
    åī
    -0.09
    otle
    -0.09
    POSITIVE LOGITS
    ErrorException
    0.09
    èĢģ人家
    0.09
    æĤ²åĵĢ
    0.08
    ãĤ¢ãĥ¼
    0.08
    æ»Ĥ
    0.08
    å¾ģ
    0.08
    orem
    0.08
    orical
    0.08
    姥
    0.07
    è§Ħå®ļ
    0.07
    Activations Density 0.216%

    No Known Activations