© 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. 56828
    Prev
    Next
    INDEX
    Explanations

    web.config settings and errors

    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
     Ank
    -0.10
    汽车产ä¸ļ
    -0.09
    äºĨå¤ļå°ij
    -0.09
    inki
    -0.09
    ]interface
    -0.09
     Edison
    -0.09
    èĭ£
    -0.09
    å¤ļå°ij
    -0.09
     hã
    -0.09
    çĻŀ
    -0.08
    POSITIVE LOGITS
    èĩªçIJĨ
    0.10
    åĨĴ
    0.09
     gel
    0.09
    游客
    0.09
    æ³°å±±
    0.08
    uhe
    0.08
    鼷éľĨ
    0.08
    OLUTION
    0.08
    opaque
    0.08
    oden
    0.08
    Activations Density 0.418%

    No Known Activations