© 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. 4758
    Prev
    Next
    INDEX
    Explanations

    domain names and subdomains

    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
    lesen
    -0.10
    cock
    -0.09
    tings
    -0.09
    lopedia
    -0.09
    ourd
    -0.09
    éľĸ
    -0.09
    èĢģ人家
    -0.08
    ấp
    -0.08
    imony
    -0.08
    ening
    -0.08
    POSITIVE LOGITS
    estic
    0.11
     dolayı
    0.10
    aries
    0.09
    åĨħçļĦ
    0.09
    mel
    0.09
    çŁ¥è¯Ĩ
    0.09
    ä¸įæ¸ħ
    0.09
    -wide
    0.09
    éĺı
    0.09
    nb
    0.09
    Activations Density 0.035%

    No Known Activations