© 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. 34142
    Prev
    Next
    INDEX
    Explanations

    Milwaukee County

    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
    è¿Ń
    -0.09
    lectic
    -0.09
    nin
    -0.08
    nan
    -0.08
    åĶ¯
    -0.08
     Newton
    -0.08
    1
    -0.08
    kü
    -0.08
    _nan
    -0.08
    bis
    -0.08
    POSITIVE LOGITS
     thượng
    0.11
    æIJŀ好
    0.10
    urre
    0.10
    æ²ħ
    0.10
    TOTYPE
    0.09
    .opens
    0.09
    flater
    0.09
    aunch
    0.09
     CALLBACK
    0.09
    æ°ĵ
    0.09
    Activations Density 0.009%

    No Known Activations