© 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. 30709
    Prev
    Next
    INDEX
    Explanations

    can help

    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
    为ä¹ĭ
    -0.09
    æĭħå¿ĥ
    -0.09
    为äºĨéģ¿åħį
    -0.09
    åıijçĶŁäºĨ
    -0.08
    è¦ģçĶ¨
    -0.08
     weighting
    -0.08
    没æľīæĥ³åĪ°
    -0.08
    éľĢè¦ģçĶ¨
    -0.08
    è£ħå¤ĩåĪ¶éĢł
    -0.08
     perse
    -0.08
    POSITIVE LOGITS
    帮åĬ©
    0.19
    èµ·åĪ°
    0.18
     помог
    0.15
    幫åĬ©
    0.15
    æıIJä¾Ľ
    0.15
    å¼ķé¢Ĩ
    0.14
    èµ·åĪ°äºĨ
    0.14
     giúp
    0.14
    帮åĬ©ä¼ģä¸ļ
    0.14
     ÑģлÑĥж
    0.14
    Activations Density 0.254%

    No Known Activations