© 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. 55571
    Prev
    Next
    INDEX
    Explanations

    consuming content or services

    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
    alis
    -0.09
    çıī
    -0.09
    èį·
    -0.09
    ä¼¼
    -0.09
    اث
    -0.08
    åĬŁå¤«
    -0.08
     padd
    -0.08
    iae
    -0.08
    æįĥ
    -0.08
    uhl
    -0.08
    POSITIVE LOGITS
    æ¶ĪèĢĹ
    0.10
    åĨł
    0.09
    æ®Ĩ
    0.09
    lsi
    0.09
    idor
    0.09
    ively
    0.09
    _consum
    0.09
    åĵij
    0.09
     Lor
    0.09
    .consume
    0.09
    Activations Density 0.026%

    No Known Activations