© 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. 55061
    Prev
    Next
    INDEX
    Explanations

    names ending in 'o' or 'i'

    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
    å§Ŀ
    -0.11
    å·¢
    -0.09
    è¿Ļéĥ¨çĶµå½±
    -0.09
    tar
    -0.09
     ìĺģíĻĶ
    -0.09
    å½±éĻ¢
    -0.09
    .gf
    -0.09
    åĩĢ
    -0.09
    AFF
    -0.09
    iesen
    -0.09
    POSITIVE LOGITS
    eg
    0.10
    ег
    0.10
    sov
    0.09
     ÑģлÑĥжбÑĭ
    0.08
    egal
    0.08
    ÑĩÑĥв
    0.08
    äºŃ
    0.08
    趵
    0.08
    æĦŁè§ī
    0.08
    å²ĺ
    0.08
    Activations Density 0.041%

    No Known Activations