© 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. 38711
    Prev
    Next
    INDEX
    Explanations

    Andrea and Andreas names

    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
    mouth
    -0.10
    çĪ·
    -0.10
    诲
    -0.09
    侧ç»ĵæŀĦæĢ§
    -0.09
    çĪº
    -0.09
     Bundy
    -0.09
    æ±°
    -0.09
    ç¯Ļ
    -0.09
    æ»Ķ
    -0.09
    ulp
    -0.09
    POSITIVE LOGITS
    icc
    0.09
    stor
    0.09
    um
    0.09
     cứ
    0.09
    nak
    0.09
    âĨĹ
    0.08
    les
    0.08
    ne
    0.08
    ender
    0.08
    MLS
    0.08
    Activations Density 0.011%

    No Known Activations