© 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. 34802
    Prev
    Next
    INDEX
    Explanations

    surgical procedures like vasectomy and hysterectomy

    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
    å¹ķ
    -0.08
    anguage
    -0.08
    ual
    -0.08
     slab
    -0.08
    éĹ
    -0.08
    uar
    -0.08
    åįĸ家
    -0.08
    æ®Ĭ
    -0.08
    åij½
    -0.08
    ç½ijè´Ń
    -0.08
    POSITIVE LOGITS
    amus
    0.09
    oise
    0.09
    _regression
    0.08
    主人
    0.08
    åħļåĴĮ
    0.08
    _pressed
    0.08
    .foreach
    0.08
    SetColor
    0.08
    绿åĮĸ
    0.08
    å¤ļä½ĻçļĦ
    0.08
    Activations Density 0.052%

    No Known Activations