© 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. 11405
    Prev
    Next
    INDEX
    Explanations

    processing

    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
    èĦī
    -0.12
    å¹ħ
    -0.11
    pulse
    -0.11
    éĺ¡
    -0.10
    èĦĪ
    -0.10
     pulse
    -0.10
    æ·®åįĹ
    -0.09
     pulses
    -0.09
     Pulse
    -0.09
    _pulse
    -0.08
    POSITIVE LOGITS
    å¤ĦçIJĨ
    0.13
    èĻķçIJĨ
    0.12
    Processing
    0.11
     processing
    0.11
    processing
    0.11
     xá»Ń
    0.11
     Processing
    0.10
     ì²ĺ리
    0.10
    åıĹçIJĨ
    0.10
    åĬŀçIJĨ
    0.10
    Activations Density 0.042%

    No Known Activations