© 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. 54345
    Prev
    Next
    INDEX
    Explanations

    not represent

    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
    è£ĺ
    -0.11
    éķĿ
    -0.10
    å®ŀä¹łçĶŁ
    -0.10
    æīĵå¼ĢäºĨ
    -0.09
    æĹħ
    -0.09
    ç¾½
    -0.09
    udy
    -0.09
    æĹ·
    -0.09
    åijĬè¯ī她
    -0.09
    ater
    -0.09
    POSITIVE LOGITS
    æѧ
    0.09
    åĪĬ
    0.08
    TAIL
    0.08
    .lt
    0.08
    并ä¸İ
    0.08
     Kapoor
    0.08
    ìĭ¬
    0.08
    FileSize
    0.08
     пÑĢе
    0.07
    phony
    0.07
    Activations Density 0.011%

    No Known Activations