© 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. 38195
    Prev
    Next
    INDEX
    Explanations

    considering, counting, or comparing

    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
    说æĺ¯
    -0.09
    _dispatcher
    -0.09
    éĢı
    -0.09
    andum
    -0.08
    æ¹Ħ
    -0.08
    öl
    -0.08
     Tight
    -0.08
    è¢Ĥ
    -0.08
    åĪĨæŀIJ
    -0.08
    abelle
    -0.08
    POSITIVE LOGITS
    åı¦è¡Į
    0.10
    ingles
    0.10
    èĩ§
    0.09
    æĮij
    0.09
    绶
    0.09
    åĵģä½į
    0.08
    amar
    0.08
    strate
    0.08
     apprec
    0.08
    æĥ³èµ·
    0.08
    Activations Density 0.020%

    No Known Activations