© 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. 32636
    Prev
    Next
    INDEX
    Explanations

    season number

    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
    çĺ¾
    -0.08
    èĥ¡åIJĮ
    -0.08
    åĵį
    -0.08
    æļ´æ¶¨
    -0.08
    çªĹ
    -0.08
    ç²¾çĽĬæ±Ĥ
    -0.08
    ldata
    -0.07
    è¿Ļè¾ĪåŃIJ
    -0.07
    ç»ĻåŃ©åŃIJ
    -0.07
    ç§ģä¸ĭ
    -0.07
    POSITIVE LOGITS
    被æ·ĺæ±°
    0.11
    ä¸įçĽ¸ä¿¡
    0.11
    æIJĵ
    0.10
    åݨ
    0.10
    OSP
    0.10
    æ·ĺæ±°
    0.09
    çĽĬ
    0.09
    çĽ¥
    0.09
    æŃ»åİ»
    0.09
    adt
    0.09
    Activations Density 0.094%

    No Known Activations