© 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. 35397
    Prev
    Next
    INDEX
    Explanations

    fortress, defence, garrison, fortified

    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
    æľĿçĿĢ
    -0.10
    æĮ¨
    -0.10
    æĭį
    -0.09
    ä½ĵè´´
    -0.08
    extent
    -0.08
    æĪIJéķ¿
    -0.08
    STAR
    -0.08
    带çĿĢ
    -0.08
    flo
    -0.08
    蹿
    -0.08
    POSITIVE LOGITS
    éĺ²åį«
    0.13
    éĺ²å¾¡
    0.13
    çĤ®
    0.12
    åł¡åŀĴ
    0.11
    ä¿Ŀå®ī
    0.10
    设æĸ½
    0.10
    éĺ²æĬ¤
    0.10
    çļĦæĪĺçķ¥
    0.09
    éĩijåĪļ
    0.09
    éĺ²çº¿
    0.09
    Activations Density 0.128%

    No Known Activations