© 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. 56363
    Prev
    Next
    INDEX
    Explanations

    young followed by person/group

    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
    è¡ħ
    -0.09
    é»ijæļĹ
    -0.09
    èĢģçĪ·åŃIJ
    -0.09
    å¤ļä¸ªåĽ½å®¶
    -0.09
    èĢģçĪ¸
    -0.08
    éĤĻ
    -0.08
    åIJı
    -0.08
    åºķå±Ĥ
    -0.08
    ä¸Ĭä¸ĭ游
    -0.08
    èħ¥
    -0.08
    POSITIVE LOGITS
    ERING
    0.10
    ặp
    0.09
    ERGE
    0.09
    EXPR
    0.08
    иÑĤе
    0.08
    ÑģÑĤв
    0.08
    ALE
    0.08
    é¬Ĩ
    0.08
    ests
    0.08
    ä¸įå¤Ł
    0.08
    Activations Density 0.024%

    No Known Activations