© 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. 47781
    Prev
    Next
    INDEX
    Explanations

    get something back

    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
    èµ·ä¼ı
    -0.08
    çĿ£å¯¼
    -0.08
     Supern
    -0.08
    éĶ¤
    -0.08
     Bene
    -0.08
    един
    -0.08
     hood
    -0.08
    çĮĹ
    -0.08
    _backend
    -0.08
    pr
    -0.07
    POSITIVE LOGITS
    æĶ¶åĽŀ
    0.18
    æī¾åĽŀ
    0.16
    åĽŀæĶ¶
    0.14
    è¿Ķè¿ĺ
    0.14
    åĽŀæĿ¥
    0.14
    åĽŀæĿ¥äºĨ
    0.13
    éĢĢè¿ĺ
    0.13
    åĽŀä¾Ĩ
    0.12
    å½ĴæĿ¥
    0.12
    丢失
    0.12
    Activations Density 0.054%

    No Known Activations