© 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. 32248
    Prev
    Next
    INDEX
    Explanations

    arranging around a core purpose

    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
    charg
    -0.09
    éģĹ产
    -0.09
    ç¾Į
    -0.09
    å¿ĥåĬ¨
    -0.09
    gend
    -0.08
    å®ħ
    -0.08
    éģĹ
    -0.08
     cru
    -0.08
    osing
    -0.08
    ä¸įå¾Ĺå·²
    -0.08
    POSITIVE LOGITS
    ä¸įå½±åĵį
    0.10
    赶ä¸Ĭ
    0.09
    ãĤĴä¸Ńå¿ĥ
    0.09
    è°ĥ度
    0.09
    å°Ĭæķ¬
    0.09
    ãĤĴä¸Ńå¿ĥãģ«
    0.09
    éģ¿å¼Ģ
    0.09
    åĽ´ç»ķ
    0.09
    çĪ±æĬ¤
    0.09
    åĪ°æĿ¥
    0.08
    Activations Density 0.060%

    No Known Activations