© 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. 16994
    Prev
    Next
    INDEX
    Explanations

    names starting with Koh/Kool/Koehl

    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
    ../
    -0.10
    ç®ĵ
    -0.09
    anga
    -0.09
     Economist
    -0.09
    械
    -0.09
    usi
    -0.08
    amen
    -0.08
    亲å±ŀ
    -0.08
    éĩıåĮĸ
    -0.08
    fruit
    -0.08
    POSITIVE LOGITS
    oom
    0.10
    ingly
    0.10
    rooms
    0.10
    wares
    0.10
    åĴ¨
    0.09
    è¿Ļæł·ä¸Ģ
    0.09
    mere
    0.09
    ä¸ĭä¸Ģ代
    0.09
    ware
    0.09
    iage
    0.09
    Activations Density 0.005%

    No Known Activations