© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 19333
    Prev
    Next
    INDEX
    Explanations

    by Names or places

    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
    æĹ¢çĦ¶
    -0.09
    èĩ¬
    -0.09
    ,[],
    -0.09
    çıĻ
    -0.08
    åİī
    -0.08
    è¾±
    -0.08
    åĶī
    -0.08
    欣åĸľ
    -0.08
    çĥ§çĥ¤
    -0.08
    èĥĮä¸Ĭ
    -0.08
    POSITIVE LOGITS
    ì·¨
    0.09
    uppe
    0.09
    usal
    0.09
    ç»ĪçĶŁ
    0.09
    вод
    0.08
    çļĦ积æŀģæĢ§
    0.08
    Frameworks
    0.08
    ystick
    0.08
    çĹ£
    0.08
     íķ¨ê»ĺ
    0.08
    Activations Density 0.065%

    No Known Activations