© 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. 7384
    Prev
    Next
    INDEX
    Explanations

    come out or go up

    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
    оÑĩка
    -0.11
    ä»ĭ
    -0.10
    åĩĨ
    -0.09
    .ico
    -0.09
    å¸ĿåĽ½
    -0.08
    ä¸ºæľŁ
    -0.08
    伪
    -0.08
    天åłĤ
    -0.08
    Ä±ÅŁ
    -0.08
     duo
    -0.08
    POSITIVE LOGITS
    没éĹ®é¢ĺ
    0.09
    Backdrop
    0.09
    7
    0.08
     beneficiary
    0.08
    2
    0.08
    ä¾ĽåºĶåķĨ
    0.08
    1
    0.08
    6
    0.08
    8
    0.08
    ä¸ĢæĿ¡
    0.08
    Activations Density 0.323%

    No Known Activations