© 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. 56899
    Prev
    Next
    INDEX
    Explanations

    basement inches deep

    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
    Õ£
    -0.09
    éĩį度
    -0.09
    æħij
    -0.09
    éĻ¤å¤ĸ
    -0.09
    渡
    -0.09
    è¿ĺè®°å¾Ĺ
    -0.08
    éĭ
    -0.08
    çĵ¯
    -0.08
    ario
    -0.08
    åĢĴåľ¨
    -0.08
    POSITIVE LOGITS
    ä¸ĩ象
    0.10
    lates
    0.09
    entai
    0.09
    åIJĮè¡Į
    0.09
    追赶
    0.08
    spacer
    0.08
     Dame
    0.08
    èĥ«
    0.08
    驾çħ§
    0.08
    legate
    0.08
    Activations Density 0.045%

    No Known Activations