© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 22332
    Prev
    Next
    INDEX
    Explanations

    philosophy

    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
    é£ŀæī¬
    -0.08
    phinx
    -0.08
    vine
    -0.08
    è¿ĻæŶ
    -0.08
    çĤ¬
    -0.08
    endant
    -0.08
    çĸ¡
    -0.08
    raphic
    -0.08
    ä¿ŀ
    -0.08
    åѤç«ĭ
    -0.08
    POSITIVE LOGITS
    åħ¬çĽĬ
    0.10
    onica
    0.09
     ÑĢаÑģпÑĢ
    0.09
    轸
    0.08
    ç¶ĵ常
    0.08
    è§ĨåIJ¬
    0.08
    å°ıæŶåīį
    0.08
     fals
    0.08
    å®ī稳
    0.08
    å¤©åºľ
    0.08
    Activations Density 0.178%

    No Known Activations