© 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. 57523
    Prev
    Next
    INDEX
    Explanations

    take a look

    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
    ä¸Ģ次次
    -0.10
    å¯Įè´µ
    -0.10
    ä¸ĢæŶ
    -0.09
     ÑĥÑģили
    -0.09
    خت
    -0.09
    溱
    -0.09
    istem
    -0.09
    caffold
    -0.09
    ä¸Ģ个éĩįè¦ģ
    -0.09
    ä¸ĢæŃ¥æŃ¥
    -0.08
    POSITIVE LOGITS
    ëį°
    0.09
    -animate
    0.08
    лÑı
    0.08
    驹
    0.08
    straint
    0.08
    æľĽåİ»
    0.08
    TOR
    0.08
    åİĨåı²ä¸Ĭ
    0.08
    specs
    0.08
    è¿Ļè¾¹
    0.08
    Activations Density 0.013%

    No Known Activations