© 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. 57061
    Prev
    Next
    INDEX
    Explanations

    consistent the whole way

    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
    çī¹åĪ¥
    -0.10
    使ä¹ĭ
    -0.09
    æµģéĢļ
    -0.09
    èı°
    -0.09
    asca
    -0.09
    .lists
    -0.09
    ainment
    -0.09
    äºĴåĬ©
    -0.09
    ä¼łæĴŃ
    -0.09
    åŁ¹è®ŃæľºæŀĦ
    -0.09
    POSITIVE LOGITS
    oton
    0.09
    è¿Ļå¼ł
    0.09
     tiếng
    0.09
     пÑĢеж
    0.09
    ä¹ĭä½ľ
    0.09
    åħ¬å¼Ģåıijè¡Į
    0.08
    çļĦä½ľåĵģ
    0.08
     sophomore
    0.08
    è¿ĽåĮĸ
    0.08
     stylist
    0.08
    Activations Density 0.072%

    No Known Activations