© 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. 19657
    Prev
    Next
    INDEX
    Explanations

    less than

    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
    asan
    -0.11
    _UNDEFINED
    -0.08
    éĻ
    -0.08
    æ¯ķç«Ł
    -0.08
    venture
    -0.08
    angkan
    -0.08
    çķ¥å¾®
    -0.08
     ÐĴаÑģ
    -0.08
     Matthias
    -0.08
    åĪ°åºķ
    -0.08
    POSITIVE LOGITS
    ened
    0.13
    /no
    0.12
    hood
    0.11
    çī¹åĪ«æĺ¯åľ¨
    0.10
     need
    0.10
    ening
    0.09
    ä¸Ģå¼Ģå§ĭå°±
    0.09
    halb
    0.09
    theless
    0.09
    åı¯è§ģ
    0.09
    Activations Density 0.041%

    No Known Activations