© 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. 11245
    Prev
    Next
    INDEX
    Explanations

    biology, pathology, physiology, anatomy

    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
    æı¡
    -0.10
    onet
    -0.08
    PKG
    -0.08
    civil
    -0.08
    alus
    -0.08
     PSU
    -0.08
    RetVal
    -0.08
    åıĹä¼Ĺ
    -0.08
    overs
    -0.08
    å¾ģæ±Ĥ
    -0.08
    POSITIVE LOGITS
    åħļåı²
    0.11
     anatomy
    0.10
     history
    0.10
    iology
    0.09
    onomy
    0.09
    atomy
    0.09
    à¸Ľà¸£à¸°
    0.09
     Ø¢ÙĦ
    0.09
    /history
    0.09
     physiology
    0.09
    Activations Density 0.307%

    No Known Activations