© 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. 49246
    Prev
    Next
    INDEX
    Explanations

    elucidate, be understood, how could

    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
    theless
    -0.10
    oline
    -0.09
    cé
    -0.09
    éĢ¡
    -0.08
    igit
    -0.08
    cluding
    -0.08
    éħ©
    -0.08
    æİĮéŨ
    -0.08
    èĩªä¿¡
    -0.08
    UpdateTime
    -0.08
    POSITIVE LOGITS
    åŀĵ
    0.08
    Zh
    0.08
     Pirate
    0.08
    åħ¶ä¸Ńæľī
    0.07
    аÐ
    0.07
     полÑĮз
    0.07
    afen
    0.07
     toll
    0.07
     XL
    0.07
    ´Ģ
    0.07
    Activations Density 2.381%

    No Known Activations