© 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. 35573
    Prev
    Next
    INDEX
    Explanations

    dates and times

    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
    utton
    -0.09
     freder
    -0.08
    iest
    -0.08
    bone
    -0.08
    ing
    -0.08
     Www
    -0.08
    åħį责声æĺİ
    -0.08
    åĨįè§ģ
    -0.08
    pot
    -0.07
    åĪĨæķ£
    -0.07
    POSITIVE LOGITS
    efault
    0.10
    coles
    0.09
    æ¡£
    0.09
    çķª
    0.09
    å¯ĮåIJ«
    0.09
    次æķ°
    0.09
    ä¿®æŃ£
    0.09
    ités
    0.09
    ileged
    0.08
    åĪ»
    0.08
    Activations Density 0.023%

    No Known Activations