© 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. 38033
    Prev
    Next
    INDEX
    Explanations

    function calls

    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
    istic
    -0.11
    ãĤ
    -0.09
    çĶ¨æĪ·æıIJä¾Ľ
    -0.09
    ä¹ĭåĬĽ
    -0.09
    å¨ģåIJį
    -0.08
    è¾ĺ
    -0.08
    笪
    -0.08
     ná»Ļp
    -0.08
    crow
    -0.08
    羣æŃ£åģļåĪ°
    -0.08
    POSITIVE LOGITS
    æĢģ
    0.10
    aroo
    0.09
    ãģĻãģIJ
    0.09
    ูล
    0.09
    ioned
    0.08
    olated
    0.08
    ernet
    0.08
    egral
    0.08
    adel
    0.08
    rd
    0.08
    Activations Density 0.252%

    No Known Activations