© 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. 31504
    Prev
    Next
    INDEX
    Explanations

    strength training exercises

    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
    iangle
    -0.09
    cope
    -0.09
    纨
    -0.08
    åIJ»
    -0.08
    /target
    -0.08
    UNCTION
    -0.08
     khá»ıi
    -0.08
    ields
    -0.08
    骧
    -0.08
    _rc
    -0.08
    POSITIVE LOGITS
    ç«Ļéķ¿
    0.09
    anax
    0.09
     ðŁĴ
    0.09
    PRESS
    0.09
    éĵħ
    0.09
    ç´łé£Ł
    0.09
    éĶ»
    0.09
    åħ´è¶£
    0.08
    inia
    0.08
    ä¹łè¿ij
    0.08
    Activations Density 0.020%

    No Known Activations