© 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. 33421
    Prev
    Next
    INDEX
    Explanations

    quantities of time

    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
    spath
    -0.10
    abor
    -0.10
    å¤ļå¤ļ
    -0.10
    ãģĻãģIJãģ«
    -0.09
    ç¬Ħ
    -0.09
    太å¤ļçļĦ
    -0.09
    hood
    -0.09
    ä¸ĬãģĮãĤĭ
    -0.09
    ãģĤãģ£ãģ¦
    -0.09
    ãģĤ
    -0.09
    POSITIVE LOGITS
     purposes
    0.11
     reasons
    0.11
     sake
    0.11
    bidden
    0.10
    reason
    0.09
    çĽĽå¤§
    0.09
    geries
    0.09
    -profit
    0.09
    ogn
    0.08
    ges
    0.08
    Activations Density 0.057%

    No Known Activations