© 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. 11114
    Prev
    Next
    INDEX
    Explanations

    xroads

    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
    estre
    -0.10
    .workflow
    -0.09
     Lamb
    -0.09
    æ³®
    -0.09
     belly
    -0.09
    çĨŁ
    -0.09
    èħ°
    -0.09
    .nt
    -0.09
    ewater
    -0.09
    梯éĺŁ
    -0.09
    POSITIVE LOGITS
    alez
    0.10
    ikal
    0.09
     Denis
    0.09
    æ£į
    0.09
    OLON
    0.08
    åĺ²
    0.08
    çĶ·å£«
    0.08
    ÑĤок
    0.08
    å¿®
    0.08
    /MIT
    0.08
    Activations Density 0.105%

    No Known Activations