© 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. 62603
    Prev
    Next
    INDEX
    Explanations

    North Carolina 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
    éĿĴæµ·çľģ
    -0.12
    涪
    -0.11
    æĪIJéĥ½å¸Ĥ
    -0.11
    å®ľå®¾
    -0.10
    è¿ĻåĿĹ
    -0.10
    绵éĺ³
    -0.10
    lain
    -0.10
     UCLA
    -0.10
    åݦéŨå¸Ĥ
    -0.10
    æµĶ
    -0.10
    POSITIVE LOGITS
    é½IJé²ģ
    0.16
    å±±ä¸ľçľģ
    0.16
    å±±ä¸ľ
    0.15
    æ²Ĥ
    0.14
    汶
    0.14
    å¨ģæµ·
    0.14
     Carolina
    0.13
    åħĸ
    0.13
    éĿĴå²Ľ
    0.13
    æ½įåĿĬ
    0.13
    Activations Density 0.230%

    No Known Activations