© 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. 56839
    Prev
    Next
    INDEX
    Explanations

    stainless steel

    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
    åģļå¾Ĺ
    -0.08
    ãģĿãģĨãģ§
    -0.08
    ãĤ½ãĥ³
    -0.08
    esor
    -0.08
    anje
    -0.08
    anj
    -0.08
    åĪĨæµģ
    -0.07
    éĥ½æĥ³
    -0.07
     limp
    -0.07
    ãģĮãģ§ãģį
    -0.07
    POSITIVE LOGITS
    aminer
    0.11
    åĬłä¸Ĭ
    0.10
    åĨįåĬłä¸Ĭ
    0.10
    羸
    0.09
    RequestId
    0.09
    trys
    0.09
    èĥ½æ»¡è¶³
    0.09
     twin
    0.09
    çŀ½
    0.09
    çļĦä¸Ģ款
    0.09
    Activations Density 0.137%

    No Known Activations