© 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
    2. Qwen3-32B
    3. 32-RESID-BATCHTOPK-65K
    4. 39655
    Prev
    Next
    INDEX
    Explanations

    his/her followed by degree or education

    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
    严å¯Ĩ
    -0.10
    èĥ¥
    -0.09
     phạm
    -0.09
    è®¤çľŁåŃ¦ä¹ł
    -0.09
    rador
    -0.08
     barg
    -0.08
    afs
    -0.08
     pok
    -0.08
    ditor
    -0.08
    ç»Ĩ
    -0.08
    POSITIVE LOGITS
    .pointer
    0.10
    à¸Ĺà¸Ķ
    0.09
    yo
    0.09
    说å®ŀ
    0.09
    ä½łè¯´
    0.08
    andle
    0.08
    udes
    0.08
    æĥ³åΰ
    0.08
    agne
    0.08
    repid
    0.08
    Activations Density 0.031%

    No Known Activations