© 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. 11162
    Prev
    Next
    INDEX
    Explanations

    getting length or size

    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
    èļģ
    -0.10
    ç»ıéªĮ丰å¯Į
    -0.09
    çĶª
    -0.09
    çİĩè¾¾
    -0.09
    æ³Ĭ
    -0.08
    ÐIJÐĿ
    -0.08
    ä¸Ńåħ³
    -0.08
    çĵ·åĻ¨
    -0.08
    lyph
    -0.08
    å¨Ł
    -0.08
    POSITIVE LOGITS
    ë§Įíģ¼
    0.11
    =size
    0.11
    大çļĦ
    0.11
     getSize
    0.10
    getSize
    0.10
    	Size
    0.10
    =len
    0.10
     size
    0.10
    å·¥å§Ķ
    0.10
    çªģ
    0.10
    Activations Density 0.798%

    No Known Activations