© 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. 2437
    Prev
    Next
    INDEX
    Explanations

    accommodating or agreeing

    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
     Coll
    -0.09
     coll
    -0.09
     Ñĩел
    -0.08
    çĦ¯
    -0.08
    _wr
    -0.08
     xét
    -0.08
     COLL
    -0.08
    coll
    -0.08
    _Property
    -0.08
    ç®Ģä»ĭ
    -0.08
    POSITIVE LOGITS
    è¿İåIJĪ
    0.17
    满足
    0.17
    éģµ
    0.15
    积æŀģéħįåIJĪ
    0.15
    顺åºĶ
    0.15
    èĥ½æ»¡è¶³
    0.15
    åĵįåºĶ
    0.15
    çŃĶåºĶ
    0.15
    滿足
    0.14
    æľįä»İ
    0.14
    Activations Density 0.095%

    No Known Activations