© 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. 61690
    Prev
    Next
    INDEX
    Explanations

    names ending in 'im', 'baum', 'ash', 'isle'

    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
    æĢİ
    -0.10
    宽
    -0.10
    ç«
    -0.10
    åŀĤ
    -0.09
    å¡Ķ
    -0.09
    æķ´çIJĨ
    -0.09
    没è§ģè¿ĩ
    -0.08
    æķ´é¡¿
    -0.08
    alle
    -0.08
     Burnett
    -0.08
    POSITIVE LOGITS
    åĽŀåĽ½
    0.11
    foreign
    0.11
    å¤ĸç±į
    0.10
    Foreign
    0.10
    侨
    0.10
     foreign
    0.10
    å¤ĸåĽ½
    0.09
    _INTERRUPT
    0.09
     Foreign
    0.09
    æľĭåıĭåľĪ
    0.09
    Activations Density 0.122%

    No Known Activations