© 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. 55332
    Prev
    Next
    INDEX
    Explanations

    yields its name

    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
    èļ±
    -0.10
    ç¯ĵ
    -0.09
    /license
    -0.09
    大åݦ
    -0.09
    åĪİ
    -0.09
    åħ±è¯Ĩ
    -0.09
    æĶ¹éĿ©åıijå±ķ
    -0.09
    .sk
    -0.09
    Ùĥب
    -0.08
    ä»ĸ们éĥ½
    -0.08
    POSITIVE LOGITS
     its
    0.14
    å®ĥçļĦ
    0.13
     Its
    0.11
     ìŀIJìĭłìĿĺ
    0.11
    åħ¶
    0.11
    Its
    0.10
     Ñģвоей
    0.10
     Ñģвои
    0.10
    èĩªèº«çļĦ
    0.10
    èĩªå·±çļĦ
    0.10
    Activations Density 0.080%

    No Known Activations