© 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. 38343
    Prev
    Next
    INDEX
    Explanations

    sidekick or side

    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
    urator
    -0.10
    å©¿
    -0.10
    å·²ä¹ħçļĦ
    -0.09
    ilor
    -0.09
    MMdd
    -0.09
    ment
    -0.09
    ting
    -0.08
    ED
    -0.08
    unting
    -0.08
    iques
    -0.08
    POSITIVE LOGITS
    kick
    0.16
    agem
    0.11
    åİ¢
    0.10
    aje
    0.10
    elay
    0.10
    å·¥ä½ľå²Ĺä½į
    0.10
    arity
    0.10
    ëģĶ
    0.10
    ë¡Ģ
    0.10
    less
    0.09
    Activations Density 0.052%

    No Known Activations