© 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. 36049
    Prev
    Next
    INDEX
    Explanations

    exclusive content or interviews

    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
    íĿ¥
    -0.10
    åĪĿæģĭ
    -0.09
    éĿ¢çĽ®
    -0.09
    åŃĺåľ¨éĹ®é¢ĺ
    -0.09
    åij¼åĶ¤
    -0.09
    soever
    -0.09
    lick
    -0.08
    ssel
    -0.08
    åij¨åĽ´çļĦ
    -0.08
    åĩºåľº
    -0.08
    POSITIVE LOGITS
    Exclusive
    0.12
     exclusive
    0.11
    exclusive
    0.11
     Exclusive
    0.11
    -exclusive
    0.11
    priv
    0.09
     паÑĢа
    0.09
    çĮ
    0.09
    ä¸ĵ
    0.09
    ended
    0.09
    Activations Density 0.008%

    No Known Activations