© 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. 18143
    Prev
    Next
    INDEX
    Explanations

    recent advances and progress

    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
    é¦ĸåĪĽ
    -0.09
    æµģ转
    -0.08
    æµ®åĬ¨
    -0.08
    ural
    -0.08
    å¾ģæ±Ĥ
    -0.08
    éĥ¤
    -0.08
    bul
    -0.08
    icut
    -0.08
    纾
    -0.08
    fil
    -0.08
    POSITIVE LOGITS
    çłĶ究人åijĺ
    0.10
    ç§ijçłĶ
    0.09
    è¿Ľå±ķ
    0.09
     иÑģÑģлед
    0.09
    ç§ijåŃ¦å®¶
    0.09
    çłĶ究
    0.09
    èĵ¦
    0.08
    åħ´è¶£
    0.08
    æĶ»åħ³
    0.08
    rena
    0.08
    Activations Density 0.542%

    No Known Activations