© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 50929
    Prev
    Next
    INDEX
    Explanations

    sacred etymology

    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
    ê°ij
    -0.11
    å¨ĺ
    -0.10
    åħļç»Ħ书记
    -0.10
    ç¯ģ
    -0.09
    chw
    -0.09
    ãĦ·
    -0.09
    bone
    -0.09
    cks
    -0.08
    ä¸įä¿¡
    -0.08
     Friendly
    -0.08
    POSITIVE LOGITS
    ä¸İåIJ¦
    0.09
    isé
    0.08
    没éĹ®é¢ĺ
    0.08
    mites
    0.08
     cows
    0.08
    /sdk
    0.08
     wg
    0.08
    æĶ¸
    0.08
    åľŁåľ°
    0.08
    çĪ
    0.07
    Activations Density 0.030%

    No Known Activations