© 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. 39945
    Prev
    Next
    INDEX
    Explanations

    familiar with his

    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
    .echo
    -0.10
    缸åºĶçļĦ
    -0.09
    washer
    -0.09
     atol
    -0.09
    缸åºĶ
    -0.09
    天ä¸ĭ
    -0.09
    è·
    -0.08
    éħįéĢģ
    -0.08
    administr
    -0.08
    structuring
    -0.08
    POSITIVE LOGITS
    æѤäºĭ
    0.13
    åħ·ä½ĵæĥħåĨµ
    0.10
    gy
    0.10
     situation
    0.09
    æĥħå½¢
    0.09
    æĥħåĨµæĿ¥çľĭ
    0.09
    å®ŀéĻħæĥħåĨµ
    0.09
     Vog
    0.09
    rapped
    0.09
    亲çĪ±
    0.09
    Activations Density 0.016%

    No Known Activations