© 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. 54600
    Prev
    Next
    INDEX
    Explanations

    richtweg, richter, licht, marquette

    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
    æİ®
    -0.08
    åģ¶åĥı
    -0.08
    è¡Į人
    -0.08
    çħ
    -0.08
    羣æŃ£åģļåĪ°
    -0.08
    heim
    -0.08
    issant
    -0.08
    æĬĺæī£
    -0.08
    د
    -0.08
    nock
    -0.08
    POSITIVE LOGITS
    æĪŁ
    0.11
    æ»ĭåij³
    0.10
    inel
    0.10
    人æŃ»äº¡
    0.10
    åĽłä¸ºä»ĸ们
    0.10
    er
    0.10
    ises
    0.10
    æİĩ
    0.09
    æijĩäºĨ
    0.09
    imal
    0.09
    Activations Density 0.002%

    No Known Activations