© 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. 7375
    Prev
    Next
    INDEX
    Explanations

    a little bit

    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
    æīĭèħķ
    -0.10
    IDD
    -0.09
    é¦Ī
    -0.08
    èļģ
    -0.08
    åīįæīĢ
    -0.08
    itÃł
    -0.08
    eer
    -0.08
    ðŁı»
    -0.08
    oot
    -0.08
    cek
    -0.08
    POSITIVE LOGITS
    tern
    0.10
    æ¯ıä¸Ģ
    0.09
    æ±ľ
    0.09
    gage
    0.09
    ìĶ©
    0.09
    æ¯ıä¸Ģ个人
    0.09
    aben
    0.09
    æĪij们就
    0.08
    ye
    0.08
    tw
    0.08
    Activations Density 0.008%

    No Known Activations