© 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. 35719
    Prev
    Next
    INDEX
    Explanations

    generation, pump, pulse, photo

    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
    åıĪè¦ģ
    -0.09
    èĶļ
    -0.09
    æĭĦ
    -0.09
    çŃĿ
    -0.09
    fort
    -0.09
    abus
    -0.08
    ä»ĸ们æĺ¯
    -0.08
    åįĥéĩĮ
    -0.08
    对ä»ĸ们
    -0.08
     Mesh
    -0.08
    POSITIVE LOGITS
    èĦī
    0.12
    è·Ĺ
    0.12
    èĦĪ
    0.10
    _pulse
    0.10
     pulse
    0.10
    çĪĨçĤ¸
    0.09
    pulse
    0.09
    .getMap
    0.09
    atos
    0.09
    .browser
    0.09
    Activations Density 0.259%

    No Known Activations