© 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. 4251
    Prev
    Next
    INDEX
    Explanations

    inclined to or predisposed

    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
    scape
    -0.10
    aceous
    -0.09
    icity
    -0.08
    第ä¸Ģ天
    -0.08
    æ½ĩ
    -0.08
    uite
    -0.08
    REAM
    -0.08
    rou
    -0.08
    ය
    -0.08
    PING
    -0.08
    POSITIVE LOGITS
    举æŃ¢
    0.10
    ìĤ¬íķŃ
    0.10
    æ·±ãģĦ
    0.10
    è®¤çľŁåŃ¦ä¹ł
    0.09
    leton
    0.09
    erman
    0.09
    ointed
    0.09
    ogie
    0.09
    verted
    0.09
    urf
    0.09
    Activations Density 0.009%

    No Known Activations