© 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. 31346
    Prev
    Next
    INDEX
    Explanations

    before or still

    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
    idy
    -0.09
    ç§į
    -0.09
     endif
    -0.09
    種
    -0.09
    æ°¨
    -0.09
    æµĬ
    -0.09
     Abr
    -0.09
    çĥŁçģ«
    -0.09
    annis
    -0.08
    ãģªãĤī
    -0.08
    POSITIVE LOGITS
    åĪļ
    0.16
    çĶ«
    0.15
    ä¸Ģå¼Ģå§ĭå°±
    0.15
    è¿ĺæľª
    0.14
    è¿ĺ没
    0.13
    å°ļæľª
    0.13
    è¿ĺ没æľī
    0.13
    å®ĮæĪIJåIJİ
    0.12
    åĪļåĪļ
    0.11
    éĤĦæ²Ĵ
    0.11
    Activations Density 0.032%

    No Known Activations