© 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. 63387
    Prev
    Next
    INDEX
    Explanations

    purpose or goal

    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¥ł
    -0.09
    åģļèµ·
    -0.09
     нев
    -0.08
    åĩĨåħ¥
    -0.08
    çĶ¨éĢĶ
    -0.08
    说æĪij
    -0.08
    åĪļæīį
    -0.08
    oad
    -0.08
    è¿ĺåĮħæĭ¬
    -0.08
    è®®é¢ĺ
    -0.08
    POSITIVE LOGITS
    追æ±Ĥ
    0.17
    缮æłĩ
    0.17
    çļĦ缮æłĩ
    0.17
    ãĤĴ缮æĮĩ
    0.16
    缮æ¨Ļ
    0.16
    goal
    0.14
    å¥ĭæĸĹ缮æłĩ
    0.14
     goal
    0.14
    ä¸ºçĽ®æłĩ
    0.14
    (goal
    0.14
    Activations Density 0.096%

    No Known Activations