© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 7084
    Prev
    Next
    INDEX
    Explanations

    reporting speech

    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
    blas
    -0.08
    èĥĥåı£
    -0.08
    èĥ½å¾ĹåĪ°
    -0.08
    éĤ£åĦ¿
    -0.08
     blas
    -0.08
     ill
    -0.08
    ä½ľèĢħæľ¬äºº
    -0.08
    ë³ij
    -0.08
    æĭ¿åĪ°äºĨ
    -0.08
    åĪį
    -0.08
    POSITIVE LOGITS
    æĹ¶è¡¨ç¤º
    0.10
    表示
    0.09
    æį®æĤī
    0.09
    екÑĤоÑĢ
    0.09
    æį®äºĨ解
    0.09
    atk
    0.08
     Eig
    0.08
     tôn
    0.08
    åıijè¨Ģ人
    0.08
    ectors
    0.08
    Activations Density 0.106%

    No Known Activations