© 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. 37637
    Prev
    Next
    INDEX
    Explanations

    thank you

    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
    à¹Ħà¸ķ
    -0.10
    mates
    -0.09
    è¦ģä¸įçĦ¶
    -0.09
    åŁ
    -0.09
    èĢģå¦Ī
    -0.09
    åĵªåĦ¿
    -0.09
    gee
    -0.09
    Descriptors
    -0.09
    éĽī
    -0.09
    leÅŁtir
    -0.08
    POSITIVE LOGITS
    oke
    0.09
    fully
    0.09
    ä¸ĵä¸ļçļĦ
    0.08
    éĤ´
    0.08
    uta
    0.08
    anner
    0.08
    ably
    0.08
    aban
    0.08
    ampus
    0.08
    antic
    0.08
    Activations Density 0.013%

    No Known Activations