© 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. 54250
    Prev
    Next
    INDEX
    Explanations

    that/those followed by a noun

    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
    icos
    -0.09
    ä¸ĢåĪĻ
    -0.09
    åħŃåIJĪ
    -0.09
    对æѤ
    -0.09
    è¡¥åħħ
    -0.08
     Dud
    -0.08
    æŃ¤é¡¹
    -0.08
    å¢ŀæ·»äºĨ
    -0.08
    ãĥĽ
    -0.08
     holidays
    -0.08
    POSITIVE LOGITS
    æģ°
    0.10
     вÑĭбÑĢ
    0.09
    zelf
    0.09
     пÑĢиÑĩ
    0.09
    monds
    0.09
    ç¬ij容
    0.09
    驾
    0.08
    Cri
    0.08
    éģĦ
    0.08
    è¿ĩç¨ĭ
    0.08
    Activations Density 0.257%

    No Known Activations