© 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. 6371
    Prev
    Next
    INDEX
    Explanations

    numbers followed by units

    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
    çİĭèĢħ
    -0.12
    ILE
    -0.09
    éªħ
    -0.09
    sembled
    -0.08
    æľīå¾Īå¤ļç§į
    -0.08
     HOLDERS
    -0.08
    beck
    -0.08
    ÑģÑĢ
    -0.08
    å·²ä¹ħçļĦ
    -0.08
    semblies
    -0.08
    POSITIVE LOGITS
    éĢĤéĩı
    0.10
     Vert
    0.09
    cript
    0.09
    ish
    0.08
    pieces
    0.08
     pieces
    0.08
    _evt
    0.08
    ç¾İ丽çļĦ
    0.08
    åĬ³åĬ¡
    0.08
     blows
    0.08
    Activations Density 0.024%

    No Known Activations