© 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. 33760
    Prev
    Next
    INDEX
    Explanations

    first story or people who found

    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
    ILLA
    -0.13
    èĤ¯å®ļ
    -0.09
    illa
    -0.09
    èĬ«
    -0.09
    .population
    -0.09
    ONS
    -0.09
    ÙĬÙĩ
    -0.08
    ç½Ħ
    -0.08
    ì»´
    -0.08
    mir
    -0.08
    POSITIVE LOGITS
    è¾¹ç¼ĺ
    0.09
    âĢİ
    0.08
    温å·ŀ
    0.08
    泯
    0.08
     edge
    0.08
    åİĨæŶ
    0.08
    缩
    0.08
    辩
    0.08
    辨
    0.08
     explor
    0.08
    Activations Density 0.564%

    No Known Activations