© 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. 63272
    Prev
    Next
    INDEX
    Explanations

    time, power, usage

    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
    åĬ²
    -0.10
     Barton
    -0.09
    otto
    -0.09
    èĦ±ç¦»
    -0.09
    eward
    -0.09
     Cha
    -0.09
    泯
    -0.09
    ocation
    -0.09
     phenomen
    -0.09
    FAIL
    -0.09
    POSITIVE LOGITS
    è¯Ŀè¯ŃæĿĥ
    0.09
     usage
    0.09
    å¸Ĥåľºä»½é¢Ŀ
    0.09
     Usage
    0.09
    èĴĤ
    0.09
    èķ²
    0.08
     USAGE
    0.08
    使çĶ¨æĿĥ
    0.08
    slots
    0.08
    ä¾Ŀæ³ķ追究
    0.08
    Activations Density 0.126%

    No Known Activations