© 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. 35909
    Prev
    Next
    INDEX
    Explanations

    understanding what/how

    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
    追æ±Ĥ
    -0.10
    ä¸įåĨįæĺ¯
    -0.09
    _dbg
    -0.09
     поÑı
    -0.09
     pursuit
    -0.09
    onet
    -0.09
    annis
    -0.08
    èĥ½è®©
    -0.08
    ÙĬÙĩ
    -0.08
    ä¸įèĥ½åĨį
    -0.08
    POSITIVE LOGITS
    èµ·çłģ
    0.14
    为åħ¶
    0.09
    çŃĶåį·
    0.09
    æī¶
    0.09
    åĵĵ
    0.08
    éĵĹ
    0.08
    åı¦å¤ĸä¸Ģ个
    0.08
    æľĢåŁºæľ¬
    0.08
    éĴ£
    0.08
    addle
    0.08
    Activations Density 0.037%

    No Known Activations