© 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. 30048
    Prev
    Next
    INDEX
    Explanations

    mutation or mutagenicity

    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
    roscope
    -0.10
    dle
    -0.09
    åĪĩåī²
    -0.09
    ãģ¡
    -0.09
    ertype
    -0.09
    anos
    -0.08
    orst
    -0.08
    å·®
    -0.08
    ause
    -0.08
    è¿«åĪĩ
    -0.08
    POSITIVE LOGITS
    iple
    0.11
    °
    0.10
    ivate
    0.09
    ìĭľíĤ¤
    0.09
    (mut
    0.09
    ãĤĤãģ®
    0.09
    agen
    0.09
    ç½ijç«Ļåľ°åĽ¾
    0.09
    ioned
    0.09
    åĬŀåħ¬åİħ
    0.09
    Activations Density 0.061%

    No Known Activations