© 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. 56046
    Prev
    Next
    INDEX
    Explanations

    calculus derivatives and code inspection

    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
    çļĦ家åºŃ
    -0.10
    çļĦèµĦéĩij
    -0.09
    çļĦ空éĹ´
    -0.09
    iec
    -0.09
    å°ı康
    -0.09
    说æĺ¯
    -0.09
    å©´
    -0.09
    为代表
    -0.09
    çļĦé£Łçī©
    -0.09
    /Area
    -0.09
    POSITIVE LOGITS
    ä¸ĺ
    0.09
    æĺ¯ä¸Ģ件
    0.09
    _CID
    0.09
     Needle
    0.08
    otime
    0.08
    rote
    0.08
    ableObject
    0.08
    needle
    0.08
     needles
    0.08
     layered
    0.08
    Activations Density 0.105%

    No Known Activations