© 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. 56949
    Prev
    Next
    INDEX
    Explanations

    in touch or divorced

    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
    olan
    -0.10
    URY
    -0.10
    ÑģеÑĢ
    -0.09
    ież
    -0.09
    éļıæŶ
    -0.09
    æŶåĪ»
    -0.09
    åĽ´çĿĢ
    -0.09
    à¹ĩà¸Ķ
    -0.09
    æºIJæºIJä¸įæĸŃ
    -0.09
    ãĥĵãĥ«
    -0.09
    POSITIVE LOGITS
    å¨ĥ
    0.09
    å¹Į
    0.09
    ToDevice
    0.09
    å¥ĩ迹
    0.08
    亡
    0.08
    apt
    0.08
    åij¤
    0.08
    adier
    0.08
    ä¸İæŶ
    0.08
    æŁIJ
    0.08
    Activations Density 0.002%

    No Known Activations