© 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. 62414
    Prev
    Next
    INDEX
    Explanations

    burying places

    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
    éĻĮçĶŁ
    -0.09
    erness
    -0.09
    ted
    -0.09
    ħ
    -0.09
    ined
    -0.09
    èĩªå¦Ĥ
    -0.09
    yr
    -0.08
    å¤ĸå©Ĩ
    -0.08
    reas
    -0.08
    enz
    -0.08
    POSITIVE LOGITS
    shire
    0.11
    çĹ¼
    0.09
    standing
    0.09
    amide
    0.09
    geois
    0.09
    otics
    0.09
    ../../../
    0.09
    teil
    0.09
    ç¬Ĩ
    0.09
    çĴł
    0.08
    Activations Density 0.004%

    No Known Activations