© 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. 56440
    Prev
    Next
    INDEX
    Explanations

    motion to / for

    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
     Ñģобой
    -0.10
    utt
    -0.09
    éĥ½ä¸įæķ¢
    -0.09
    ois
    -0.09
    绩
    -0.08
    orado
    -0.08
    åİŁæľīçļĦ
    -0.08
    compat
    -0.08
    ocha
    -0.08
    setUp
    -0.08
    POSITIVE LOGITS
    çİł
    0.09
    éĺ¿æĭī
    0.08
    书ä¸Ń
    0.08
    arseille
    0.08
    æĪijåİ»
    0.08
     ÙĪعÙĨ
    0.08
    ä¸ŃåįİæĸĩåĮĸ
    0.08
    gio
    0.08
    ç½ijåıĭè¯Ħ论
    0.08
    oppel
    0.08
    Activations Density 0.015%

    No Known Activations