© 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. 56045
    Prev
    Next
    INDEX
    Explanations

    from date

    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
    æĸ°ä¸ĸ纪
    -0.09
    åı¸
    -0.09
    æĢ¥
    -0.08
    åºł
    -0.08
     Jude
    -0.08
    uce
    -0.08
    irc
    -0.08
    ä¸ĸ纪
    -0.08
     struct
    -0.08
     Cust
    -0.08
    POSITIVE LOGITS
    åĮĹ京æŶéĹ´
    0.12
    ç½ķ
    0.09
    å½ĵåľ°æŶéĹ´
    0.09
    ERRU
    0.09
    åĬª
    0.09
    _KERNEL
    0.09
    éŃij
    0.09
    uchos
    0.09
    .Unknown
    0.08
     اÙĦÙĨظر
    0.08
    Activations Density 0.026%

    No Known Activations