© 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. 20250
    Prev
    Next
    INDEX
    Explanations

    javadoc or programming code files

    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
    iece
    -0.09
    èĩªåªĴä½ĵ
    -0.09
    æ·±å¤ľ
    -0.09
    åħ¨è¿ĩç¨ĭ
    -0.09
    arent
    -0.09
    说æľį
    -0.08
    CVE
    -0.08
     Gems
    -0.08
     Homes
    -0.08
    çļĦèĥĮåIJİ
    -0.08
    POSITIVE LOGITS
    çĦ¦
    0.08
    ç«ĭãģ¡
    0.08
    AYER
    0.08
    æĪIJé¾Ļ
    0.08
    owo
    0.08
    åĮĹæŀģ
    0.08
    éĥĽ
    0.08
    aries
    0.08
    vention
    0.08
    ниÑĨÑĭ
    0.08
    Activations Density 0.168%

    No Known Activations