© 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. 57829
    Prev
    Next
    INDEX
    Explanations

    general manager, secretary, counsel

    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
    ç§ĭåŃ£
    -0.09
    主è¦ģçĶ¨äºİ
    -0.09
    åĿ¡
    -0.09
    åħ±åIJĮåĬªåĬĽ
    -0.09
    å±ij
    -0.09
    âĹĥ
    -0.09
    alic
    -0.09
    缸åħ³äººåijĺ
    -0.08
    çŁŃæŶéĹ´åĨħ
    -0.08
     Ñĩем
    -0.08
    POSITIVE LOGITS
    sut
    0.08
    ieder
    0.08
    è´£ç¼ĸ
    0.08
    èĬ
    0.08
    ä»ħ代表
    0.08
    radi
    0.08
    è°ĥçļ®
    0.08
    indy
    0.07
    天é¹ħ
    0.07
    owie
    0.07
    Activations Density 0.011%

    No Known Activations