© 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. 19688
    Prev
    Next
    INDEX
    Explanations

    well

    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
    çħŀ
    -0.09
    INAL
    -0.09
    -0.09
    æ¸Ń
    -0.08
    èĻIJ
    -0.08
    æĹłæĥħ
    -0.08
    à¸Īำ
    -0.08
    illo
    -0.08
    éĤ£è¾¹
    -0.08
    apat
    -0.08
    POSITIVE LOGITS
    ibri
    0.09
    ibox
    0.09
    tower
    0.09
    æĺ¯åľ¨
    0.09
    agens
    0.09
    ढ
    0.09
    ÑĢеÑģÑĤ
    0.09
    reno
    0.09
    à¹Ħà¸ĭ
    0.09
    gren
    0.09
    Activations Density 0.011%

    No Known Activations