© 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. 49013
    Prev
    Next
    INDEX
    Explanations

    file system

    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
    æĶ¿åºľéĥ¨éŨ
    -0.09
    ifer
    -0.09
    .prof
    -0.08
    cosa
    -0.08
    ķ
    -0.08
    ALE
    -0.08
    NotNull
    -0.08
    pch
    -0.08
    å¨ģå°Ķ
    -0.08
    æĥ³åĬŀæ³ķ
    -0.08
    POSITIVE LOGITS
    :///
    0.12
    /ec
    0.09
    ×ĵ×Ļ×Ŀ
    0.09
    åİļ度
    0.09
    ARING
    0.09
    .clips
    0.08
    mers
    0.08
    tering
    0.08
    çĸ£
    0.08
    ugen
    0.08
    Activations Density 0.079%

    No Known Activations