© 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. 23898
    Prev
    Next
    INDEX
    Explanations

    point

    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
    æĿIJ
    -0.11
    Ticks
    -0.09
    顶
    -0.09
    iazza
    -0.09
    èİĨ
    -0.09
    æľªæĪIJ
    -0.08
     Graves
    -0.08
    ActionCreators
    -0.08
    é£İåIJ¹
    -0.08
    оÑĢо
    -0.08
    POSITIVE LOGITS
    çĤ¹
    0.20
     point
    0.17
    é»ŀ
    0.16
    point
    0.16
    çĤ¹äºĨ
    0.15
    points
    0.15
     points
    0.15
    ä¹ĭå¤Ħ
    0.13
    _point
    0.13
    çĤ¹åĦ¿
    0.13
    Activations Density 0.091%

    No Known Activations