© 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. 31953
    Prev
    Next
    INDEX
    Explanations

    vast majority

    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
    åİ©
    -0.09
    ombo
    -0.09
    æĻ®
    -0.09
    çł´è£Ĥ
    -0.08
    åŃĹåı·
    -0.08
    åĬ£
    -0.08
    ÑįÑĢ
    -0.08
    _emit
    -0.08
    ÑĦикÑģ
    -0.08
    vey
    -0.08
    POSITIVE LOGITS
    ç»Ŀ大éĥ¨åĪĨ
    0.28
    大éĥ¨åĪĨ
    0.28
    ç»Ŀ大å¤ļæķ°
    0.27
    大å¤ļæķ°
    0.26
    å¤ļæķ°
    0.25
     majority
    0.25
     ëĮĢë¶Ģë¶Ħ
    0.22
    大å¤ļæķ°äºº
    0.21
    大éĥ¨åĪĨ人
    0.20
    大å¤ļ
    0.18
    Activations Density 0.095%

    No Known Activations