© 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. 1815
    Prev
    Next
    INDEX
    Explanations

    pride and proud

    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
    .motion
    -0.08
    ignon
    -0.08
    æŃ¤æ¬¡
    -0.08
    èŀĥèŁ¹
    -0.08
    ç¾İ
    -0.08
    æ¸ĹéĢı
    -0.08
    cki
    -0.08
    è¯ļæĦı
    -0.07
    åĨĬ
    -0.07
    Ñĩи
    -0.07
    POSITIVE LOGITS
    æ°ĺ
    0.10
    æ¦Ī
    0.10
    ê°IJ
    0.10
    ç²³
    0.09
    楣
    0.09
     defends
    0.09
    åıijå±ķéĺ¶æ®µ
    0.09
    çĤ«èĢĢ
    0.09
    é«ĺæĸ°
    0.09
    å²Ĺä½į
    0.09
    Activations Density 0.011%

    No Known Activations