© 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. 54192
    Prev
    Next
    INDEX
    Explanations

    weight and height

    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
    ç½ijæ°ij
    -0.09
    俱
    -0.08
    fell
    -0.08
    èľĪ
    -0.08
    ç½ijåıĭ
    -0.08
    iglia
    -0.08
    é«ĺ度
    -0.08
     espos
    -0.08
    çļĦç»ĵæŀľ
    -0.08
    åIJĽ
    -0.08
    POSITIVE LOGITS
    ä½ĵéĩį
    0.11
     weight
    0.10
    æľªå©ļ
    0.09
    charset
    0.09
     Weight
    0.09
    -weight
    0.09
     Urb
    0.09
     WEIGHT
    0.09
    .Weight
    0.08
    weight
    0.08
    Activations Density 0.017%

    No Known Activations