© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 10175
    Prev
    Next
    INDEX
    Explanations

    separators or buffers

    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
    inkle
    -0.11
    æı½
    -0.10
    çĥ
    -0.10
    严åİīæīĵåĩ»
    -0.09
    Peripheral
    -0.09
    å¤ĸåĽ´
    -0.09
    éĢģåİ»
    -0.09
    å°ĺ
    -0.09
    ibold
    -0.09
    èĩªæĿ¥
    -0.09
    POSITIVE LOGITS
    å±Ĥ
    0.10
    udas
    0.10
    ä¸Ģå±Ĥ
    0.10
     layer
    0.09
    çīĩ
    0.09
     layers
    0.09
    åŀ«
    0.09
    ActionResult
    0.08
    Layer
    0.08
    íĮ©
    0.08
    Activations Density 0.094%

    No Known Activations