© 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. 21848
    Prev
    Next
    INDEX
    Explanations

    enrolled in

    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
    -0.11
    /rfc
    -0.09
    _TER
    -0.09
    -hearted
    -0.09
    éĤĤ
    -0.08
    é¼IJ
    -0.08
    严éĩįçļĦ
    -0.08
    fully
    -0.08
    ä¸įåĩºæĿ¥
    -0.08
    é«ĺä¸ŃçĶŁ
    -0.08
    POSITIVE LOGITS
    OrUpdate
    0.12
    çĻ»è®°
    0.10
    ables
    0.10
    resher
    0.09
    ments
    0.09
    æĸ°ä¸ĸ纪
    0.09
     PROT
    0.09
    idable
    0.08
    (register
    0.08
    atas
    0.08
    Activations Density 0.017%

    No Known Activations