© 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. 5751
    Prev
    Next
    INDEX
    Explanations

    ties it all together

    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
    æĺ±
    -0.10
    å¹½
    -0.10
    èĦ¸
    -0.09
     завод
    -0.09
     Rig
    -0.09
    书åĨĻ
    -0.08
    REEN
    -0.08
     Epstein
    -0.08
    omy
    -0.08
    çŁ³åĮĸ
    -0.08
    POSITIVE LOGITS
    æķ´åIJĪ
    0.15
    综åIJĪ
    0.14
    ç»ĵåIJĪèµ·æĿ¥
    0.12
    åįıè°ĥ
    0.11
    綾åIJĪ
    0.11
    综åIJĪæķ´æ²»
    0.11
    综åIJĪæĢ§
    0.10
    æĬĬæݧ
    0.10
    绣ä¸Ģ
    0.10
    纽带
    0.10
    Activations Density 0.073%

    No Known Activations