© 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. 57367
    Prev
    Next
    INDEX
    Explanations

    involved in, late in, welcome to

    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
    ä¸ĢæīĢ
    -0.08
    strup
    -0.08
    /flutter
    -0.08
     Hag
    -0.08
    çīł
    -0.08
    chedulers
    -0.08
    çĻ¸
    -0.08
    .func
    -0.07
    ä¸ĢåıĮ
    -0.07
    mia
    -0.07
    POSITIVE LOGITS
    å®ł
    0.09
    åĹij
    0.08
    rack
    0.08
     rack
    0.08
    éĤł
    0.08
    warnings
    0.08
    _SCROLL
    0.08
    stor
    0.08
    avis
    0.07
    寸
    0.07
    Activations Density 1.295%

    No Known Activations