© 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. 23496
    Prev
    Next
    INDEX
    Explanations

    Lagrange

    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
    lop
    -0.10
    èģĶè°Ĭ
    -0.09
    åıijçĥŃ
    -0.09
    track
    -0.09
    czas
    -0.08
    istra
    -0.08
    ilation
    -0.08
    switch
    -0.08
    lock
    -0.08
    ÑĢоÑģ
    -0.08
    POSITIVE LOGITS
    ainer
    0.10
    uers
    0.09
    å§Ķ
    0.09
    à¹Ģà¸ī
    0.09
    ëį°
    0.08
     toItem
    0.08
    .gwt
    0.08
    .hm
    0.08
    andra
    0.08
     forCell
    0.08
    Activations Density 0.009%

    No Known Activations