© 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. 19075
    Prev
    Next
    INDEX
    Explanations

    electrical insulation and voltage breakdown

    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
    人æµģ
    -0.11
    磫æŃ£
    -0.10
    èĩªæķij
    -0.10
    å¾Īæĸ¹ä¾¿
    -0.10
    å®īåħ¨ä¿Ŀéļľ
    -0.09
    вÑıз
    -0.09
    便åĪ©
    -0.09
    æµģéĢļ
    -0.09
    è´Łæĭħ
    -0.09
    å®īåħ¨æĦŁ
    -0.09
    POSITIVE LOGITS
    åĩ»
    0.09
    çĶµæ°Ķ
    0.09
     Äijiá»ĥn
    0.08
    bara
    0.08
    Expose
    0.08
     Hav
    0.08
    äºķ
    0.08
    rious
    0.08
    严
    0.08
    ctors
    0.08
    Activations Density 0.095%

    No Known Activations