© 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. 1509
    Prev
    Next
    INDEX
    Explanations

    Cairo, Nile, Egypt, E. coli

    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
    çĦ¶æĺ¯
    -0.13
    еÑĢÑĮ
    -0.10
    wayne
    -0.10
     паÑĢа
    -0.09
    ãĤ·ãĥ³
    -0.09
    çľ¼çľĭ
    -0.08
    roman
    -0.08
    еÑĩ
    -0.08
    รา
    -0.08
    ycle
    -0.08
    POSITIVE LOGITS
     Naw
    0.09
    åij±
    0.09
     Mell
    0.09
    èĿĩ
    0.09
    IED
    0.09
    ied
    0.09
    ienne
    0.09
    ç³Ĭ
    0.09
    meld
    0.08
    éĻĮ
    0.08
    Activations Density 0.013%

    No Known Activations