© 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. 17261
    Prev
    Next
    INDEX
    Explanations

    those explaining following nouns

    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
    istro
    -0.09
    ä»Ģä¹Īåij¢
    -0.08
    ichten
    -0.08
    aju
    -0.08
    çªĿ
    -0.08
    ipo
    -0.08
     feas
    -0.08
     wysoko
    -0.08
    æĸ½
    -0.08
    loy
    -0.08
    POSITIVE LOGITS
    æıĨ
    0.10
    çı©
    0.10
    磨
    0.10
    èĿł
    0.10
    æ¨ĺ
    0.09
    chap
    0.09
    åĴ¦
    0.09
    è¿ĻæĶ¯
    0.09
    çIJ¢
    0.09
    Parts
    0.08
    Activations Density 0.048%

    No Known Activations