© 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. 19218
    Prev
    Next
    INDEX
    Explanations

    development and growth

    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
    å£ķ
    -0.09
    主æĦı
    -0.09
    çĵł
    -0.08
     Cha
    -0.08
    çģ¼
    -0.08
    æķijåij½
    -0.08
    é¢Ħæ¡Ī
    -0.08
    ÑģÑĤавка
    -0.08
    åģļçļĦäºĭæĥħ
    -0.08
    ĮĢ
    -0.08
    POSITIVE LOGITS
     development
    0.16
    æĪIJéķ¿ä¸º
    0.15
    åıijå±ķ
    0.15
    æĪIJéķ¿
    0.15
    åģ¥åº·æĪIJéķ¿
    0.15
    åħ¨éĿ¢åıijå±ķ
    0.14
    çĻ¼å±ķ
    0.14
    æĪIJéķ·
    0.14
    åıijå±ķçļĦ
    0.13
    åıijå±ķä¸Ń
    0.13
    Activations Density 0.194%

    No Known Activations