© 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. 27358
    Prev
    Next
    INDEX
    Explanations

    applies to

    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
    ê°Ŀ
    -0.10
    éĿ¢åĮħ
    -0.09
    è§ļ
    -0.09
    ule
    -0.09
    åħ¬äº¤
    -0.08
     habit
    -0.08
    åĽ½å®¶æĪĺçķ¥
    -0.08
    åij¨æģ©
    -0.08
    affe
    -0.08
    çłĶ究ä¸Ńå¿ĥ
    -0.08
    POSITIVE LOGITS
    ä»»ä½ķæŶåĢĻ
    0.11
    èĢĮè¨Ģ
    0.10
    æīĢæľī人
    0.09
    enis
    0.08
    enson
    0.08
    éĤ£äºĽ
    0.08
    erner
    0.08
    etr
    0.08
    ç²Ĵ
    0.08
    çĽ²çĽ®
    0.08
    Activations Density 0.088%

    No Known Activations