© 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. 55993
    Prev
    Next
    INDEX
    Explanations

    sintered, collapsed, density, pressed, compressed

    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
    顺åĬ¿
    -0.11
    éĢ¡
    -0.10
    è¤Ĭ
    -0.10
    hra
    -0.10
    æ¡Ĩ
    -0.09
    æ¶Į
    -0.09
    åŃĶéĽĢ
    -0.08
    -redux
    -0.08
    ufe
    -0.08
    ERA
    -0.08
    POSITIVE LOGITS
    irst
    0.10
    æĸ¥
    0.10
    磶
    0.09
     ден
    0.09
     tinder
    0.09
    low
    0.09
    å¡Į
    0.09
    èģĭ
    0.09
    éĺ²æݧ
    0.08
    irm
    0.08
    Activations Density 0.141%

    No Known Activations