© 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. 58732
    Prev
    Next
    INDEX
    Explanations

    Psy, psych, psi, YC, yll

    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
    ä¸ĢéŨ
    -0.10
    éĩįç»Ħ
    -0.09
    adr
    -0.09
    åİĨåı²æĸĩåĮĸ
    -0.09
    aign
    -0.09
    ernel
    -0.09
    ç¼ķ
    -0.08
    壮
    -0.08
    nite
    -0.08
    çķ
    -0.08
    POSITIVE LOGITS
    è¯¾æľ¬
    0.09
    èĭ¦èĭ¦
    0.09
    ä¸Ńä¿¡
    0.08
    骢
    0.08
    åŃ¦æł¡çļĦ
    0.08
    çģ¸
    0.08
    éĹ»
    0.08
    ahkan
    0.08
    åĩºç§Ł
    0.08
    æĸĽ
    0.08
    Activations Density 0.003%

    No Known Activations