© 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. 23464
    Prev
    Next
    INDEX
    Explanations

    Company names and abbreviations

    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
    ôm
    -0.10
    aced
    -0.10
    æŃ£å½ĵ
    -0.09
    men
    -0.09
    asl
    -0.09
     XL
    -0.09
    èĽŃ
    -0.08
    OSC
    -0.08
    èĨ³
    -0.08
    XL
    -0.08
    POSITIVE LOGITS
    ç»Ģ
    0.09
    _DEN
    0.09
    ibi
    0.08
    è°Ĭ
    0.08
     evacuate
    0.08
    ipur
    0.08
    ä¸ĢåĪĩéĥ½
    0.08
    佶
    0.08
    æĶ¶åĪ°äºĨ
    0.08
     pomp
    0.08
    Activations Density 0.003%

    No Known Activations