© 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. 52818
    Prev
    Next
    INDEX
    Explanations

    and therefore

    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
    èľĥ
    -0.10
    éģĤ
    -0.10
     Cousins
    -0.10
    icie
    -0.09
    еÑģÑĮ
    -0.09
    .tm
    -0.09
    綦
    -0.09
     Hole
    -0.09
    .updateDynamic
    -0.09
    clid
    -0.09
    POSITIVE LOGITS
    ered
    0.09
    w
    0.09
    warm
    0.08
     assortment
    0.08
    ering
    0.08
    ende
    0.08
     qu
    0.08
     fast
    0.07
    诸å¦Ĥ
    0.07
    åı¦ä¸Ģä½į
    0.07
    Activations Density 0.236%

    No Known Activations