© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 62399
    Prev
    Next
    INDEX
    Explanations

    Motley Crue, JBZoo.com, NLS, ISO

    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
    æ²Ĩ
    -0.09
    8
    -0.09
    7
    -0.09
    4
    -0.09
    çĻ¾åIJĪ
    -0.08
     banning
    -0.08
    odal
    -0.08
    驼
    -0.08
    5
    -0.08
    /t
    -0.08
    POSITIVE LOGITS
    ä»Ģä¹Īä¸ľè¥¿
    0.10
    zelf
    0.10
    æĴŃæĬ¥
    0.09
    ugin
    0.09
    _mes
    0.09
    éĽ³
    0.09
    ä¸ľè¥¿
    0.09
    ä»Ģä¹Īåij¢
    0.09
    éĩįçĤ¹å·¥ä½ľ
    0.09
    æĹ¥å¸¸å·¥ä½ľ
    0.09
    Activations Density 0.002%

    No Known Activations