© 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. 4111
    Prev
    Next
    INDEX
    Explanations

    world or planet

    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
    fait
    -0.11
    ä¸ĢäºĮ
    -0.09
    alo
    -0.09
    é£Łçī©
    -0.08
    _HAL
    -0.08
    èĹĵ
    -0.08
    Inspectable
    -0.08
    iami
    -0.08
    æģ¬
    -0.08
    å¾Īå¤ļæľĭåıĭ
    -0.08
    POSITIVE LOGITS
    è¿Ļ个æŶåĢĻ
    0.11
    анÑģ
    0.09
    èİ«è¿ĩäºİ
    0.09
    ฯ
    0.09
    ãģķãĤī
    0.09
    elle
    0.08
    åīįåįģ
    0.08
    beeld
    0.08
    çľĭå®Į
    0.08
    /out
    0.08
    Activations Density 0.020%

    No Known Activations