© 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. 33544
    Prev
    Next
    INDEX
    Explanations

    training and education programs

    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
    伸åĩº
    -0.10
    Ñĩи
    -0.10
    æĺ¶
    -0.09
    AppComponent
    -0.09
    çļĦèĥ½éĩı
    -0.09
    为æ°ij
    -0.09
    表çĻ½
    -0.09
    _sdk
    -0.09
    çľĩ
    -0.09
    å®ŀè´¨
    -0.08
    POSITIVE LOGITS
    åѦåijĺ
    0.14
    åŁ¹è®Ń
    0.13
    3
    0.10
    åħļæł¡
    0.10
    æ¡Īä¾ĭ
    0.10
    4
    0.10
    çłĶ究éĻ¢
    0.10
    æ·±åĮĸæĶ¹éĿ©
    0.09
    7
    0.09
    1
    0.09
    Activations Density 0.045%

    No Known Activations