© 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. 32977
    Prev
    Next
    INDEX
    Explanations

    paperback, paper, back

    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
    otec
    -0.09
    ively
    -0.09
    ÅĽcie
    -0.08
    è§Ī
    -0.08
    former
    -0.08
    ibus
    -0.08
    端æŃ£
    -0.08
    å¾ĹäºĨ
    -0.08
     MediaPlayer
    -0.08
     бил
    -0.07
    POSITIVE LOGITS
    åľŃ
    0.10
    opoulos
    0.10
    -Version
    0.09
    åħ¬å¼ĢèµĽ
    0.09
    æľīå¾Īå¤ļç§į
    0.08
    æĭľ
    0.08
    wares
    0.08
    注æĺİæĿ¥æºIJ
    0.08
    aval
    0.08
    AGING
    0.08
    Activations Density 0.004%

    No Known Activations