© 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. 61107
    Prev
    Next
    INDEX
    Explanations

    license or Copyright

    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
    ä¸įéĻIJ
    -0.10
    æ´Ĺ
    -0.09
    ç®ĢåİĨ
    -0.09
    ä¹ĭ家
    -0.09
     latin
    -0.09
    å½ĵéĢī
    -0.08
    çĵľ
    -0.08
    æĦĨ
    -0.08
     jer
    -0.08
     ENV
    -0.08
    POSITIVE LOGITS
    åĽ¿
    0.11
    iaÅĤ
    0.09
    ather
    0.09
    åķľ
    0.09
    çłļ
    0.09
    ogn
    0.09
    èĶ·
    0.09
    åħ³åĪĩ
    0.09
    èĸ°
    0.08
    ç¼ķ
    0.08
    Activations Density 0.006%

    No Known Activations