© 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. 10313
    Prev
    Next
    INDEX
    Explanations

    pets and their owners

    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
    ine
    -0.11
    -eyed
    -0.10
    iani
    -0.09
    å¤ĸç±į
    -0.09
    æĸ°åħ´
    -0.09
    æ¯Ķäºļ
    -0.09
    -wing
    -0.09
    ses
    -0.09
    å±ħ
    -0.09
    æķħ宫
    -0.08
    POSITIVE LOGITS
    tings
    0.10
    Åij
    0.10
    onga
    0.09
    verständlich
    0.09
    yped
    0.09
    tain
    0.08
    åľ¨æİ¥åıĹ
    0.08
    itized
    0.08
    nels
    0.08
    ted
    0.08
    Activations Density 0.007%

    No Known Activations