© 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. 3815
    Prev
    Next
    INDEX
    Explanations

    state names and court or governmental titles

    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
    åĬ³
    -0.10
    æ±°
    -0.10
    äºķ
    -0.10
    ä»ij
    -0.10
    berger
    -0.09
    æµ¦ä¸ľ
    -0.09
    åĭŀ
    -0.09
    éĺĬ
    -0.09
    ALSE
    -0.09
    LEncoder
    -0.09
    POSITIVE LOGITS
    寡
    0.09
    igest
    0.08
    æľŁåĨħ
    0.08
    èķ¤
    0.08
     sax
    0.08
     WHITE
    0.08
    asmus
    0.08
    gap
    0.08
    ä¸Ģæ³¢
    0.08
    åѤåįķ
    0.08
    Activations Density 0.265%

    No Known Activations