© 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. 3256
    Prev
    Next
    INDEX
    Explanations

    being said

    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
    åıĪ好
    -0.09
    å¿ĥåºķ
    -0.09
     обÑĬÑıвл
    -0.08
    еÑģÑĤво
    -0.08
    _orient
    -0.08
    çļĦçIJĨçĶ±
    -0.08
    ESCO
    -0.08
    /location
    -0.08
     Scalars
    -0.08
     amounts
    -0.08
    POSITIVE LOGITS
    cin
    0.10
    人们对
    0.09
    æĿ¡çº¦
    0.09
     cand
    0.09
    åĽ½æ°ij
    0.09
    ä¹ĭéĻħ
    0.09
    产ä¸ļåĽŃåĮº
    0.09
    ÑģÑĤÑĭ
    0.08
    ville
    0.08
    åįĥåı¤
    0.08
    Activations Density 0.067%

    No Known Activations