© 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. 39694
    Prev
    Next
    INDEX
    Explanations

    remixed, removable, remap, remaster, remodel, removal

    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
    ames
    -0.10
    جاÙĦ
    -0.10
    etypes
    -0.10
    umpy
    -0.10
    ernes
    -0.09
    uate
    -0.09
    osite
    -0.09
    Ñģкоп
    -0.09
    olas
    -0.08
    éķ°
    -0.08
    POSITIVE LOGITS
    ders
    0.12
    /rem
    0.10
    aney
    0.10
    endez
    0.10
    der
    0.09
    yle
    0.09
    ittance
    0.08
    ovable
    0.08
    phis
    0.08
    perature
    0.08
    Activations Density 0.034%

    No Known Activations