© 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. 33510
    Prev
    Next
    INDEX
    Explanations

    or something

    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
    å·«
    -0.11
    ä¾®
    -0.11
    åij¦
    -0.09
    опÑĢеделен
    -0.09
    åĿĿ
    -0.09
    ogen
    -0.09
    åĸĦ
    -0.09
    åħŃ个æľĪ
    -0.09
    ucene
    -0.09
    äºĶåĪĨéĴŁ
    -0.09
    POSITIVE LOGITS
     latter
    0.10
    åľ¨åħ¶
    0.10
    GEST
    0.09
    失
    0.09
    类似çļĦ
    0.09
    缸è¿ij
    0.08
    PMC
    0.08
    iode
    0.08
    chy
    0.08
    iem
    0.08
    Activations Density 0.015%

    No Known Activations