© 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. 31458
    Prev
    Next
    INDEX
    Explanations

    long, rolling, burst, mouthfeel

    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
    æ±²
    -0.09
    å·§åIJĪ
    -0.08
    å¤Ħäºİ
    -0.08
    ëł¹
    -0.08
    çĶŁéķ¿
    -0.08
    .dispatchEvent
    -0.08
    幸
    -0.08
    å¤Ħ
    -0.07
    ä¿¡ä»»
    -0.07
    .FileNotFoundException
    -0.07
    POSITIVE LOGITS
    åĽŀåij³
    0.10
    è¾¹éĻħ
    0.10
    éļıä¹ĭ
    0.10
    Fant
    0.09
    å¯ĮåĬĽ
    0.09
    èij
    0.09
    èĪĮ
    0.09
    åIJ¬è¯Ŀ
    0.09
    èĢ³è¾¹
    0.09
    çĸijä¼¼
    0.09
    Activations Density 0.035%

    No Known Activations