© 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. 48528
    Prev
    Next
    INDEX
    Explanations

    least followed by 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
    ä¹ĭä½Ļ
    -0.09
    å¯Ħ
    -0.09
    .dt
    -0.08
    ath
    -0.08
    åıªä¸įè¿ĩ
    -0.08
    ç¥ļ
    -0.08
     almond
    -0.08
    zeug
    -0.07
    å°ģ
    -0.07
    fort
    -0.07
    POSITIVE LOGITS
    å¤ļå°ijéĴ±
    0.11
    åįģåĩłä¸ª
    0.10
    æ¶Īæģ¯ç§°
    0.10
    pong
    0.10
    伺
    0.10
    bian
    0.10
    .toByteArray
    0.09
    çļĦçĹĩçĬ¶
    0.09
    ç³ľ
    0.09
    两åij¨
    0.09
    Activations Density 0.164%

    No Known Activations