© 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. 3820
    Prev
    Next
    INDEX
    Explanations

    state of

    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
     ÑģÑĢедÑģÑĤва
    -0.09
    æīįç®Ĺ
    -0.09
    åĬ£
    -0.09
    æĸ¹åı¯
    -0.08
    群ä½ĵ
    -0.08
    omen
    -0.08
    éĺµéĺµ
    -0.08
    æĶ»
    -0.08
    adies
    -0.08
    ä¸Ńæľī
    -0.08
    POSITIVE LOGITS
    æ´»çĿĢ
    0.09
    layan
    0.09
    ä¸Ģ级
    0.08
    à¹ģà¸ĸ
    0.08
    iki
    0.08
    人çī©
    0.08
    ensed
    0.08
    LM
    0.08
    墨西åĵ¥
    0.08
     getState
    0.08
    Activations Density 0.040%

    No Known Activations