© 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. 50188
    Prev
    Next
    INDEX
    Explanations

    seasonal descriptor

    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
    esis
    -0.10
    åĴĴ
    -0.09
    opies
    -0.09
    hip
    -0.09
    opic
    -0.09
    ialis
    -0.09
    é²ľè¡Ģ
    -0.09
    æī¾åĩĨ
    -0.08
    ç»ĿæľĽ
    -0.08
     Gors
    -0.08
    POSITIVE LOGITS
    iste
    0.09
    iday
    0.09
    åįģæľĪ
    0.09
    aunch
    0.09
    åįĥ
    0.08
    cloak
    0.08
    /OR
    0.08
    acious
    0.08
    ings
    0.08
    acie
    0.08
    Activations Density 0.010%

    No Known Activations