© 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. 33950
    Prev
    Next
    INDEX
    Explanations

    IBM Corporation

    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
    åįĹå®ģå¸Ĥ
    -0.10
    ç«Ļåľ¨
    -0.10
    ä¼°åĢ¼
    -0.10
     Oregon
    -0.09
    éŀ
    -0.09
    Oregon
    -0.09
    éĥ´
    -0.09
    LEG
    -0.09
    çļĩ
    -0.09
    ç¾İ人
    -0.09
    POSITIVE LOGITS
     IBM
    0.17
    IBM
    0.15
    .ibm
    0.13
    é²ħ
    0.12
    è¾½å®ģçľģ
    0.10
    大è¿ŀ
    0.10
    è¾½å®ģ
    0.10
    (ib
    0.10
    vig
    0.09
     Wisconsin
    0.09
    Activations Density 0.120%

    No Known Activations