© 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. 58771
    Prev
    Next
    INDEX
    Explanations

    ramp, rampaging, ramped up

    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
    ÂŃt
    -0.10
    顽
    -0.10
    swire
    -0.10
    æĭĤ
    -0.09
    WRAPPER
    -0.09
    头éĥ¨
    -0.09
     crow
    -0.09
    ëĭī
    -0.09
    quee
    -0.09
    身åŃIJ
    -0.09
    POSITIVE LOGITS
     ramp
    0.09
    ä¸ĢæĹı
    0.08
    èĤĩ
    0.08
    ä¸Ģè§Ĵ
    0.08
    ç¨ĭ度
    0.08
    monkey
    0.08
    EventManager
    0.08
    éĦ¢
    0.08
     Pin
    0.08
    æѤæĸĩ
    0.08
    Activations Density 0.066%

    No Known Activations