© 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. 33596
    Prev
    Next
    INDEX
    Explanations

    digital technologies, virtual learning, tax, healthcare

    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
    æĪ³
    -0.09
    æ¶Ł
    -0.08
     Lux
    -0.08
    èĬĤæĹ¥
    -0.08
    çĽĪ
    -0.08
    çĶľçĶľ
    -0.08
    缴å±ŀ
    -0.08
    icum
    -0.08
    å¼ĥ
    -0.08
    icism
    -0.08
    POSITIVE LOGITS
    è¾ħåĬ©
    0.13
    交æĺĵå¹³åı°
    0.11
    èĻļæĭŁ
    0.10
    olls
    0.10
    åĬŀåħ¬
    0.10
    å·¥ä½ľæķĪçİĩ
    0.09
     virtual
    0.09
     Schl
    0.09
    æľīåĬ©
    0.09
    çĭį
    0.09
    Activations Density 0.207%

    No Known Activations