© 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. 2340
    Prev
    Next
    INDEX
    Explanations

    content posted or uploaded

    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
    çĭİ
    -0.10
    ATUS
    -0.10
    _REPORT
    -0.10
     Reported
    -0.09
    é¹ĥ
    -0.09
    REPORT
    -0.09
    åŃķèĤ²
    -0.09
    hardware
    -0.09
    åIJij举
    -0.09
    _UNDEFINED
    -0.09
    POSITIVE LOGITS
     posted
    0.14
     posting
    0.11
     uploaded
    0.10
     public
    0.10
    åľ¨ç½ijä¸Ĭ
    0.10
    åħ¬å¸ĥ
    0.10
    Uploaded
    0.10
     Posting
    0.09
     rect
    0.09
    Posting
    0.09
    Activations Density 0.173%

    No Known Activations