© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 50528
    Prev
    Next
    INDEX
    Explanations

    mid-year, mid-season, mid-century

    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
    mach
    -0.09
    gom
    -0.09
    UME
    -0.08
    /be
    -0.08
    fit
    -0.08
    termination
    -0.08
    é¢Ĩ
    -0.08
    enz
    -0.08
    æijĺè¦ģ
    -0.08
    导å¸Ī
    -0.08
    POSITIVE LOGITS
    PostBack
    0.10
    çĬ¶æĢģä¸ĭ
    0.09
    髦
    0.09
    æĥ´
    0.09
    Ñģан
    0.08
    ä¹ĭç¾İ
    0.08
    åį´åıijçİ°
    0.08
    мел
    0.08
    lds
    0.08
    olson
    0.08
    Activations Density 0.021%

    No Known Activations