© 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. 61277
    Prev
    Next
    INDEX
    Explanations

    web addresses and file extensions

    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
    微信群
    -0.09
    uckle
    -0.09
     THROW
    -0.08
    å®ĺç½ij
    -0.08
    kening
    -0.08
    stash
    -0.08
    AppComponent
    -0.08
    abad
    -0.08
    è¯¾æľ¬
    -0.08
    ÑĢе
    -0.07
    POSITIVE LOGITS
    æŃ£å¥½
    0.09
    éĢIJ
    0.09
    éĢłè¡Ģ
    0.09
    åĪļ好
    0.09
    iamond
    0.09
    å¥
    0.09
    æª
    0.09
    åĨĻçĿĢ
    0.09
    椰
    0.09
    onia
    0.08
    Activations Density 0.128%

    No Known Activations