© 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. 48342
    Prev
    Next
    INDEX
    Explanations

    Libreoffice Draw foundation options

    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
     ephem
    -0.08
     Barker
    -0.08
    reece
    -0.08
    ãĥĭãĥĥãĤ¯
    -0.08
    伫
    -0.08
    éŁŃ
    -0.08
    fund
    -0.08
     Morr
    -0.08
    rees
    -0.08
    殿ä¸ĭ
    -0.08
    POSITIVE LOGITS
    沤
    0.12
    æ³·
    0.12
    æ±¾
    0.11
     Nos
    0.09
    åĬ¨åijĺ
    0.09
    é³ŀ
    0.09
    .document
    0.09
    æijĬ
    0.09
    è¿©
    0.09
    éĶ»çĤ¼
    0.08
    Activations Density 0.134%

    No Known Activations