© 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
    2. Qwen3-32B
    3. 32-RESID-BATCHTOPK-65K
    4. 17354
    Prev
    Next
    INDEX
    Explanations

    video bandwidth and noise

    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
    aid
    -0.10
    åŀŃ
    -0.10
    èĤ
    -0.09
    åĬ©ãģij
    -0.09
    渥
    -0.09
    èĤĥ
    -0.09
    èĩªæķij
    -0.08
    æīĵåĩº
    -0.08
    æį£
    -0.08
    ä¸Ģ声
    -0.08
    POSITIVE LOGITS
    ä¸īåĪĨ
    0.10
    沤
    0.09
    Ownership
    0.09
    Propagation
    0.08
    entifier
    0.08
    atsu
    0.08
     Malone
    0.08
    chos
    0.08
    ours
    0.08
    Poster
    0.08
    Activations Density 0.228%

    No Known Activations