© 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. 19246
    Prev
    Next
    INDEX
    Explanations

    telescope and visual instruments

    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
    éļħ
    -0.09
    çĥ«
    -0.09
    æ½į
    -0.08
    gu
    -0.08
    warz
    -0.08
    activate
    -0.08
    åľºä¸Ĭ
    -0.08
     SU
    -0.08
    ingly
    -0.08
    amina
    -0.08
    POSITIVE LOGITS
    æľĽ
    0.12
    ä¼½
    0.11
    ä¸ļä½Ļ
    0.10
    åij¨å¹´
    0.10
     visuals
    0.09
     telesc
    0.09
     Telescope
    0.09
     Instruments
    0.09
    otos
    0.09
    åıĭè°Ĭ
    0.09
    Activations Density 0.181%

    No Known Activations