© 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. 18271
    Prev
    Next
    INDEX
    Explanations

    Kindle, Alexa, Kylie Jenner

    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
    ½æķ°
    -0.10
    bins
    -0.08
    acus
    -0.08
    Bindings
    -0.08
    ÑĥÑĪ
    -0.08
     Shooter
    -0.08
    /sbin
    -0.08
    ustain
    -0.08
    nah
    -0.08
    ifact
    -0.08
    POSITIVE LOGITS
    maid
    0.10
    zer
    0.10
    ãģªãĤĬ
    0.10
    ough
    0.09
    éľı
    0.09
    /pdf
    0.09
    æĬī
    0.09
    REE
    0.09
    trap
    0.09
    å¨ĺ家
    0.09
    Activations Density 0.004%

    No Known Activations