© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 55863
    Prev
    Next
    INDEX
    Explanations

    more and more

    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
    rophe
    -0.10
    çī¹æ®ĬæĥħåĨµ
    -0.10
    ä½ıäºĨ
    -0.10
     Chambers
    -0.09
    adin
    -0.09
     hoạch
    -0.09
    roomId
    -0.09
    achable
    -0.09
    éĢ¡
    -0.09
    æĢĥ
    -0.09
    POSITIVE LOGITS
    ãĢħ
    0.16
    麻
    0.09
    éĺĻ
    0.09
    à¹Ĩ
    0.08
    æĭĹ
    0.08
    oes
    0.08
    ly
    0.08
    Accent
    0.08
     times
    0.08
     Happ
    0.08
    Activations Density 0.027%

    No Known Activations