© 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. 62824
    Prev
    Next
    INDEX
    Explanations

    advantages and their benefits

    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
    mates
    -0.10
    cape
    -0.10
    èĻ±
    -0.10
    ings
    -0.09
    sis
    -0.09
    weet
    -0.09
    ì¦Ŀ
    -0.09
    ers
    -0.09
    INGS
    -0.09
    妪
    -0.09
    POSITIVE LOGITS
    ably
    0.14
    ously
    0.13
    ively
    0.12
    åľ°ä½į
    0.11
    lä
    0.11
    ANCED
    0.10
    ancement
    0.10
    iali
    0.10
    /dis
    0.09
    ially
    0.09
    Activations Density 0.021%

    No Known Activations