© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 51052
    Prev
    Next
    INDEX
    Explanations

    complex descriptive nouns

    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
    uite
    -0.10
    ä¸Ģå¥Ĺ
    -0.10
    cape
    -0.09
    ponent
    -0.09
    '
    -0.09
    åįģæĿ¡
    -0.09
    afe
    -0.08
    å°ijä¸įäºĨ
    -0.08
    ymbol
    -0.08
    phere
    -0.08
    POSITIVE LOGITS
    们
    0.19
    åĢij
    0.18
    们çļĦ
    0.17
    swith
    0.16
    们éĥ½
    0.14
    sWith
    0.13
    ëĵ¤ìĿ´
    0.13
    sto
    0.13
    ëĵ¤ìĿĢ
    0.12
    ëĵ¤ìĹIJê²Į
    0.11
    Activations Density 1.099%

    No Known Activations