© 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. 48549
    Prev
    Next
    INDEX
    Explanations

    by itself or themselves

    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
    trak
    -0.08
    åĪ°æľŁ
    -0.08
     Burl
    -0.08
    igu
    -0.08
    suming
    -0.08
     colle
    -0.08
    æľŁéĹ´
    -0.08
    urg
    -0.08
     Wig
    -0.08
    å°ıæľĭåıĭ
    -0.08
    POSITIVE LOGITS
    สว
    0.11
    _rd
    0.10
    esto
    0.09
    å¯Ł
    0.09
    éĹŃ
    0.09
    _RW
    0.08
    èĥľåĪ©
    0.08
    å°ģ
    0.08
     SWT
    0.08
    ERVE
    0.08
    Activations Density 0.058%

    No Known Activations