© 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. 48275
    Prev
    Next
    INDEX
    Explanations

    spark computing and electronics

    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
    ç¬ijè¯Ŀ
    -0.10
    compass
    -0.09
    ária
    -0.09
    íħĮ
    -0.08
     Panc
    -0.08
    ä¸įçĶĺ
    -0.08
    entr
    -0.08
    acious
    -0.08
    experimental
    -0.08
    isi
    -0.08
    POSITIVE LOGITS
    ä¸įç»ı
    0.12
    Ñİ
    0.10
    lander
    0.09
    lesh
    0.09
    çĦķ
    0.09
    manship
    0.09
    licht
    0.09
    祸
    0.09
    èİ«
    0.09
    èĥ´
    0.09
    Activations Density 0.007%

    No Known Activations