© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 59446
    Prev
    Next
    INDEX
    Explanations

    luck and ford

    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
    Negative Logits
     McCart
    -0.10
    åħļå§Ķ书记
    -0.10
    ocities
    -0.10
    onta
    -0.09
    éĺµåľ°
    -0.09
    IDGE
    -0.09
    á»ĩt
    -0.09
    icens
    -0.09
    æĸ¯é¡¿
    -0.09
    ugar
    -0.09
    POSITIVE LOGITS
    ron
    0.09
    à¸Ĭะ
    0.09
    rise
    0.08
    ché
    0.08
    è°ĭ
    0.08
    AZY
    0.08
    åIJĮæľŁ
    0.08
    fé
    0.08
    azy
    0.08
    çŁŃ
    0.08
    Activations Density 0.005%

    No Known Activations