© 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. 22941
    Prev
    Next
    INDEX
    Explanations

    expert opinion

    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
    หมà¸Ķ
    -0.10
    nable
    -0.10
    erman
    -0.10
    nier
    -0.10
    otte
    -0.09
    yard
    -0.09
    ned
    -0.08
    å¿«ä¹IJ
    -0.08
    INGS
    -0.08
    inear
    -0.08
    POSITIVE LOGITS
    ise
    0.14
    ises
    0.10
    ials
    0.10
    iny
    0.10
    人士
    0.10
    icient
    0.09
    _TUN
    0.09
    laÅŁ
    0.09
    rimon
    0.09
    ãģĻãģİãĤĭ
    0.09
    Activations Density 0.016%

    No Known Activations