© 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. 58850
    Prev
    Next
    INDEX
    Explanations

    wrecksites

    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
     spy
    -0.10
     spies
    -0.10
    å¾ĩ
    -0.10
    rens
    -0.09
    èĬ¬åħ°
    -0.09
     pan
    -0.09
    spy
    -0.08
    åħij
    -0.08
    以éĺ²
    -0.08
    .spark
    -0.08
    POSITIVE LOGITS
    ÃŃculo
    0.10
    ç¤ģ
    0.10
    çļĦæĦıè§ģ
    0.09
     Bail
    0.09
    ighter
    0.09
     wre
    0.09
     Heard
    0.09
    æ½ľ
    0.09
    áĥ¯
    0.09
    ãĤ«ãĥ³
    0.09
    Activations Density 0.135%

    No Known Activations