© 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. 50953
    Prev
    Next
    INDEX
    Explanations

    berry and fruit descriptions

    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
    éªĦ
    -0.09
    åľĪåŃIJ
    -0.09
    家éĩĮ
    -0.09
    manifest
    -0.09
    olle
    -0.08
    ubb
    -0.08
     manh
    -0.08
    3
    -0.08
    åŁºç¤İ
    -0.08
    é³ŀ
    -0.08
    POSITIVE LOGITS
    éªĿ
    0.11
    红éħĴ
    0.10
    rosso
    0.10
    红èī²
    0.09
    çı²
    0.09
    红æĹĹ
    0.09
    æŀľæ±ģ
    0.09
    erval
    0.09
    æµĨ
    0.09
    æ®ĸ
    0.09
    Activations Density 0.045%

    No Known Activations