© 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. 35453
    Prev
    Next
    INDEX
    Explanations

    zone, uranium, zero, open, den, lines, Triangle

    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
    驾
    -0.11
    oved
    -0.10
    澡
    -0.09
    åįı
    -0.09
    é¾Ľ
    -0.09
     spiked
    -0.09
    工夫
    -0.09
    çĪ±åIJĥ
    -0.09
    OTE
    -0.09
    大佬
    -0.09
    POSITIVE LOGITS
    åĤ»
    0.12
    å®ľå±ħ
    0.09
    burgh
    0.09
    ë¬ĺ
    0.09
    .misc
    0.08
    åľ°å¸¦
    0.08
    _clr
    0.08
    LEASE
    0.08
    å¼ĢåıijåĮº
    0.08
    ä¸Ģç±»
    0.08
    Activations Density 0.046%

    No Known Activations