© 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. 61679
    Prev
    Next
    INDEX
    Explanations

    high school people and activities

    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
    缸åıį
    -0.10
    èĮ§
    -0.10
    é«ĺçŃīåŃ¦æł¡
    -0.10
    åĽłåŃIJ
    -0.10
     Ñģобой
    -0.10
    å°ıé¢Ŀ贷款
    -0.09
    æľŁåĨħ
    -0.09
    SCP
    -0.09
    ìĤ¬íķŃ
    -0.09
    .setCursor
    -0.09
    POSITIVE LOGITS
    涯
    0.10
    ers
    0.10
    -level
    0.10
    aged
    0.09
    -aged
    0.09
    ë§Īëĭ¤
    0.08
    PING
    0.08
    eros
    0.08
    erna
    0.08
    ogeneous
    0.08
    Activations Density 0.023%

    No Known Activations