© 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. 39207
    Prev
    Next
    INDEX
    Explanations

    following "from"

    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
    èĿī
    -0.10
     từng
    -0.09
    ä»ħæľī
    -0.09
    sted
    -0.08
    çĦī
    -0.08
    зам
    -0.08
    åģľä¸ĭ
    -0.08
    vvm
    -0.08
    æIJ¦
    -0.08
    ä»Ģä¹Īåı«
    -0.08
    POSITIVE LOGITS
    æľīç§į
    0.10
    iped
    0.10
    omics
    0.09
    åĪ
    0.08
    pers
    0.08
     whence
    0.08
    ØŃس
    0.08
    åĹŁ
    0.08
    å¤ĸåįĸ
    0.08
    бÑĢ
    0.08
    Activations Density 0.129%

    No Known Activations