© 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. 39632
    Prev
    Next
    INDEX
    Explanations

    change of state

    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
    quires
    -0.11
    åĬŀçIJĨ
    -0.11
     воÑĤ
    -0.10
    eut
    -0.10
    嵬
    -0.10
    íĦ°
    -0.09
    arti
    -0.09
    ynet
    -0.09
    pering
    -0.09
    à¸łà¸²à¸ŀ
    -0.09
    POSITIVE LOGITS
    æŀ¶åŃIJ
    0.11
    äºĨä»ĸçļĦ
    0.10
    ning
    0.10
    äºĨæĪijçļĦ
    0.09
    amon
    0.09
    дан
    0.08
    åĺī
    0.08
    aled
    0.08
    æİīäºĨ
    0.08
    ï¸
    0.08
    Activations Density 0.015%

    No Known Activations