© 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. 57843
    Prev
    Next
    INDEX
    Explanations

    ground state, shipping, breaking, floor, system

    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
    ä¸ŃéĢĶ
    -0.10
     Gors
    -0.10
     Tops
    -0.10
    éĿ¢åŃĶ
    -0.09
    çĥ¨
    -0.09
    à¸Ħà¸Ńย
    -0.08
    sects
    -0.08
    éºŁ
    -0.08
    -valu
    -0.08
    errar
    -0.08
    POSITIVE LOGITS
    -ground
    0.10
     ground
    0.09
    ground
    0.09
    ä¸Ģ线
    0.09
    laden
    0.09
    å¾Ĺå¾Ī好
    0.09
    Ground
    0.08
    otype
    0.08
    çĻ½å¤©
    0.08
    ¿
    0.08
    Activations Density 0.024%

    No Known Activations