© 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. 23345
    Prev
    Next
    INDEX
    Explanations

    subsub projectsub forumsub menusub familiasub querysub-4 metresubscriberssubmers

    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
     tamp
    -0.09
    碴
    -0.08
     Weiter
    -0.08
     tả
    -0.08
    uppe
    -0.08
    éķ¿çŁŃ
    -0.08
    anguard
    -0.08
    gMaps
    -0.08
    ician
    -0.08
    å¼ĩ
    -0.08
    POSITIVE LOGITS
    posed
    0.09
    scribers
    0.09
    aries
    0.09
    身影
    0.09
    untu
    0.09
    riere
    0.09
    åĽ«
    0.09
    åİļåİļ
    0.09
    åĹ£
    0.09
    mers
    0.08
    Activations Density 0.040%

    No Known Activations