© 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. 38124
    Prev
    Next
    INDEX
    Explanations

    but not limited to

    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
    èµ·åĪĿ
    -0.09
    aqu
    -0.09
    antha
    -0.09
    _DRV
    -0.09
    ç«ŀäºīä¼ĺåĬ¿
    -0.08
    çªŁ
    -0.08
    çŃ·åŃIJ
    -0.08
    isters
    -0.08
    èIJ
    -0.08
    geist
    -0.08
    POSITIVE LOGITS
    ings
    0.09
    emo
    0.09
    INGS
    0.09
    à¸Ńม
    0.09
    åķĨåѦéĻ¢
    0.08
    EDI
    0.08
    ä¸Ĭåİ»
    0.08
    çļĦ表æĥħ
    0.08
    argo
    0.08
    éĩįä¸Ńä¹ĭéĩį
    0.08
    Activations Density 0.415%

    No Known Activations