© 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. 3517
    Prev
    Next
    INDEX
    Explanations

    in

    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
    èĬĤ
    -0.09
    quia
    -0.09
     cred
    -0.09
    èŁł
    -0.09
    çĽ¸äº²
    -0.09
    çģ«çĤ¬
    -0.08
     запиÑģи
    -0.08
    кал
    -0.08
     Timothy
    -0.08
    IndexOf
    -0.08
    POSITIVE LOGITS
    è¿ĽæĿ¥
    0.13
     ëĵ¤ìĸ´
    0.12
    è¿Ľåİ»
    0.11
    Parms
    0.09
    wards
    0.09
    à¹Ģà¸Ĥ
    0.08
    äºĴéĢļ
    0.08
    -Out
    0.08
    outs
    0.08
    /out
    0.08
    Activations Density 0.117%

    No Known Activations