© 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. 11767
    Prev
    Next
    INDEX
    Explanations

    Slavic and other place names

    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
    nger
    -0.08
    otics
    -0.08
     Jam
    -0.08
    èį»
    -0.08
    ooter
    -0.08
    ables
    -0.08
    inks
    -0.08
    æĦ«
    -0.08
    urre
    -0.07
    ucks
    -0.07
    POSITIVE LOGITS
    æĻ´
    0.09
    å½ĵå±Ģ
    0.09
    /Set
    0.08
    è¿Ļ家åħ¬åı¸
    0.08
     Medal
    0.08
    foy
    0.08
    åįĬ天
    0.08
    nid
    0.08
     reve
    0.08
    ä¸Ģ家
    0.08
    Activations Density 0.386%

    No Known Activations