© 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. 27325
    Prev
    Next
    INDEX
    Explanations

    code or markup structure

    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
    vern
    -0.08
    åħ¶å®ĥéĹ®é¢ĺ
    -0.08
    ]]></
    -0.08
    åĥ»
    -0.08
    rove
    -0.08
     INCIDENT
    -0.08
    cancelled
    -0.08
    .finished
    -0.07
    æŶéļĶ
    -0.07
    åĻ«
    -0.07
    POSITIVE LOGITS
    çıł
    0.11
    éĴĵ
    0.10
    å¥ļ
    0.09
    横
    0.09
    åī©ä¸ĭçļĦ
    0.09
    èİ·å¾ĹæĽ´å¤ļ
    0.09
    dish
    0.08
    è§ĩ
    0.08
    çļ¿
    0.08
    press
    0.08
    Activations Density 0.017%

    No Known Activations