© 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. 53656
    Prev
    Next
    INDEX
    Explanations

    Studios, amusement rides

    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
    è«ĸ
    -0.11
    论
    -0.10
    åĬŀåħ¬æ¥¼
    -0.10
    èĪ·
    -0.09
    åĽºå®ļçļĦ
    -0.09
     Admir
    -0.09
    cola
    -0.09
    éłĺåŁŁ
    -0.09
     amore
    -0.09
    å®īå±ħ
    -0.09
    POSITIVE LOGITS
    éĹ¨ç¥¨
    0.08
    ç¹ģ
    0.08
    åħµé©¬
    0.08
     Vig
    0.08
    ocket
    0.08
    ered
    0.07
     Center
    0.07
     ail
    0.07
    ä¸Ńå¿ĥ
    0.07
    èĥľ
    0.07
    Activations Density 0.014%

    No Known Activations