© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 20140
    Prev
    Next
    INDEX
    Explanations

    browsing shops

    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
    饯
    -0.12
    çįŃ
    -0.09
    Lu
    -0.09
    jaw
    -0.09
    æ®ļ
    -0.09
    ikal
    -0.09
     tempor
    -0.08
    UserProfile
    -0.08
    ä¸įæĸŃæıIJåįĩ
    -0.08
    æĴ¤ç¦»
    -0.08
    POSITIVE LOGITS
    é¦Ĩ
    0.11
    éĻĪåĪĹ
    0.11
    å·¥ä½ľäººåijĺ
    0.10
    æŀ¶åŃIJ
    0.10
    å±ķåĵģ
    0.10
    æĮĤçīĮ
    0.10
    å±ķåİħ
    0.09
    æİĴéĺŁ
    0.09
    ä¸ĵåĮº
    0.09
    éĤ£éĩĮ
    0.09
    Activations Density 0.063%

    No Known Activations