© 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. 35112
    Prev
    Next
    INDEX
    Explanations

    grab something

    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
    ØŃر
    -0.10
    åĭī强
    -0.10
    yr
    -0.10
    tle
    -0.09
    odor
    -0.08
     вообÑīе
    -0.08
    vation
    -0.08
    halb
    -0.08
     dÃłng
    -0.08
    ãģ°
    -0.08
    POSITIVE LOGITS
    ä¸ĢæĬĬ
    0.13
    åıijå±ķæľºéģĩ
    0.12
    æľºéģĩ
    0.10
    ../../../
    0.10
    ðŁı»
    0.10
    éĺĦ
    0.10
    èĽ¸
    0.09
    shaw
    0.09
    ĩ
    0.09
    deen
    0.09
    Activations Density 0.011%

    No Known Activations