© 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. 6879
    Prev
    Next
    INDEX
    Explanations

    below punctuation

    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
    æľ«
    -0.09
    ovo
    -0.09
    åĽŀ头
    -0.09
    对ä¸įèµ·
    -0.09
    罩
    -0.09
    èIJ½
    -0.08
    æ¦ľ
    -0.08
    轧
    -0.08
    ç©´
    -0.08
    _WRONG
    -0.08
    POSITIVE LOGITS
    仿
    0.12
    æ¡Ķ
    0.09
    çŀ©
    0.09
    俦
    0.08
    æĹĦ
    0.08
    ë§ī
    0.08
    лÑİд
    0.08
    ile
    0.08
    aviolet
    0.08
    åħµé©¬
    0.08
    Activations Density 0.019%

    No Known Activations