© 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. 55180
    Prev
    Next
    INDEX
    Explanations

    fast-paced and rapidly changing

    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
    yar
    -0.10
    .GetBytes
    -0.09
    å°¼æĸ¯
    -0.09
    _nat
    -0.09
    åĬłçıŃ
    -0.09
     deutschland
    -0.09
    产èĥ½
    -0.09
    ajor
    -0.09
    åĽ½å®¶éĺŁ
    -0.08
    orrent
    -0.08
    POSITIVE LOGITS
     chóng
    0.10
    /high
    0.09
    å¿«éĢŁ
    0.09
    /fast
    0.09
    éĩijåįİ
    0.09
     rapidly
    0.09
    è¿ħ
    0.08
    ä¿ĥ
    0.08
    åĿİ
    0.08
    御
    0.08
    Activations Density 0.038%

    No Known Activations