© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 19769
    Prev
    Next
    INDEX
    Explanations

    demand for or requirements

    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
    aked
    -0.11
    ../../
    -0.10
    itness
    -0.10
    omal
    -0.09
    ctic
    -0.09
    ../../../
    -0.09
    ï¸
    -0.09
    adin
    -0.09
    GRAM
    -0.09
    omo
    -0.08
    POSITIVE LOGITS
    å·²ä¹ħçļĦ
    0.13
    uset
    0.13
    侧ç»ĵæŀĦæĢ§
    0.13
    æĻ¯å¾·
    0.11
    AnimationFrame
    0.10
    æĹºçĽĽ
    0.10
     dÄ±ÅŁÄ±
    0.09
    -driven
    0.09
    åĴĮåıijå±ķ
    0.09
    è¾Ħ
    0.09
    Activations Density 0.024%

    No Known Activations