© 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. 61238
    Prev
    Next
    INDEX
    Explanations

    truth be told

    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
    åĬŁ
    -0.09
    æĹ¶è¾°
    -0.09
    sc
    -0.09
    elly
    -0.09
    imator
    -0.09
    çݳ
    -0.08
    (dec
    -0.08
    à¹Ģสà¸Ļ
    -0.08
    äºŁ
    -0.08
    itude
    -0.08
    POSITIVE LOGITS
    éĢıéľ²
    0.11
    便ä¼ļ
    0.10
    /rfc
    0.09
    minster
    0.09
    çĦķåıij
    0.09
    éĿ
    0.08
    èĢĢ
    0.08
    èĭ±çī¹
    0.08
    æĪij羣çļĦ
    0.08
    ä¼łåĩº
    0.08
    Activations Density 0.003%

    No Known Activations