© 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. 58073
    Prev
    Next
    INDEX
    Explanations

    optimal or imal

    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
    porte
    -0.10
    bies
    -0.10
    aman
    -0.10
    abouts
    -0.09
    foot
    -0.09
    appa
    -0.08
    CNT
    -0.08
    æĭŃ
    -0.08
    outs
    -0.08
    noch
    -0.08
    POSITIVE LOGITS
    æľĢä½³
    0.12
    mium
    0.12
    人å±ħ
    0.11
    æĥħåĨµä¸ĭ
    0.11
     обÑĢазом
    0.11
    ä¹ĭä½ľ
    0.10
    ply
    0.10
    imal
    0.10
    imum
    0.10
    æŶéĹ´åĨħ
    0.10
    Activations Density 0.018%

    No Known Activations