© 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. 36166
    Prev
    Next
    INDEX
    Explanations

    build number or identifier

    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
    çķĶ
    -0.09
    åıijå±ķ缮æłĩ
    -0.08
    éĻĽ
    -0.08
    lain
    -0.08
    åı¤èĢģçļĦ
    -0.08
    assin
    -0.08
    _CALLBACK
    -0.08
    æ®ĩ
    -0.08
    漫éķ¿çļĦ
    -0.08
    DOC
    -0.08
    POSITIVE LOGITS
    ings
    0.10
    ght
    0.09
    è¡Ķ
    0.09
    s
    0.09
    inary
    0.09
    æ¶ĵ
    0.08
     trÃŃ
    0.08
    овиÑĩ
    0.08
    entifier
    0.08
    å¤©åºľ
    0.08
    Activations Density 0.055%

    No Known Activations