© 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. 19861
    Prev
    Next
    INDEX
    Explanations

    assembling or setting up

    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
    æºħ
    -0.10
    åĮ£
    -0.09
    æĪ´çĿĢ
    -0.09
    inia
    -0.09
    æĪ´
    -0.09
    éģįåıĬ
    -0.09
    åıĤè§Ĥ
    -0.09
    çĽ
    -0.09
    çĵ¶
    -0.09
     McGregor
    -0.09
    POSITIVE LOGITS
    ç»Ħè£ħ
    0.12
     dismantle
    0.09
     dismant
    0.09
    ometrics
    0.09
    æĶ¯æŁ±
    0.08
    éħ©
    0.08
    é¢Ĥ
    0.08
    .components
    0.08
     assembly
    0.08
    åľ¨åľ°ä¸Ĭ
    0.08
    Activations Density 0.073%

    No Known Activations