© 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. 3417
    Prev
    Next
    INDEX
    Explanations

    the fact is that

    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
    al
    -0.10
    å¯Ħæīĺ
    -0.08
    æ¬łç¼º
    -0.08
     curt
    -0.08
    hr
    -0.08
    èİĴ
    -0.08
    7
    -0.08
    æĢİä¹Ī说
    -0.08
    3
    -0.08
     opposite
    -0.08
    POSITIVE LOGITS
    æĽ´éĩįè¦ģçļĦ
    0.16
    æĽ´éĩįè¦ģ
    0.14
    éĻ¤æѤ
    0.13
    æĽ´è¦ģ
    0.12
    驱
    0.10
    ä¹ĭå¤ĸ
    0.10
    ãģłãģijãģ§ãģªãģı
    0.10
    éĻ¤æѤä¹ĭå¤ĸ
    0.10
    éŃ
    0.10
    uke
    0.10
    Activations Density 0.092%

    No Known Activations