© 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. 31868
    Prev
    Next
    INDEX
    Explanations

    verified via

    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
    å³¥
    -0.09
    娴
    -0.09
    è°ĥçłĶ
    -0.09
    åıijå±ķåīįæĻ¯
    -0.09
    plib
    -0.08
    ìĦ¸
    -0.08
    Sk
    -0.08
    ãģĮãĤī
    -0.08
    anium
    -0.08
    æµģéĢĿ
    -0.08
    POSITIVE LOGITS
    åħ¥åĽŃ
    0.10
    å®īä¿Ŀ
    0.10
    åħ¥åľº
    0.10
     билеÑĤ
    0.10
    è¿Ľåľº
    0.10
     vendors
    0.10
     eventId
    0.10
    _guide
    0.10
    å¤ĸåĽ´
    0.09
    è´Ń票
    0.09
    Activations Density 0.158%

    No Known Activations