© 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. 54432
    Prev
    Next
    INDEX
    Explanations

    code snippets with program identifiers

    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
    arend
    -0.10
    æ·ĩ
    -0.10
    anja
    -0.09
    æ·ĺå®Ŀ
    -0.09
    éĥ¦
    -0.09
    ç¡Ĵ
    -0.09
    Await
    -0.09
    ä½£
    -0.08
    egov
    -0.08
    antha
    -0.08
    POSITIVE LOGITS
    å¹ħ
    0.10
    çĹ´
    0.09
    hai
    0.09
    TypeEnum
    0.09
    _dll
    0.09
    DC
    0.09
    å¸ĸ
    0.09
    oba
    0.09
    è´´
    0.08
    SDK
    0.08
    Activations Density 0.394%

    No Known Activations