© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 36813
    Prev
    Next
    INDEX
    Explanations

    can be done

    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
    éĶģ
    -0.10
    gué
    -0.09
    ìĩĦ
    -0.09
    .mem
    -0.09
     Lock
    -0.09
    ä½İä¼°
    -0.09
    æĨº
    -0.09
    å¹Ħ
    -0.09
    .Unlock
    -0.09
     LOCK
    -0.09
    POSITIVE LOGITS
    ncy
    0.10
    绵
    0.10
    anna
    0.08
    YPD
    0.08
    绾
    0.08
    åŁºå±Ĥ
    0.08
     eff
    0.08
    æĿĤ
    0.08
     absor
    0.08
    æ°ijå¿ĥ
    0.08
    Activations Density 0.070%

    No Known Activations