© 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. 5224
    Prev
    Next
    INDEX
    Explanations

    technical queries or code snippets

    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
     Fou
    -0.09
    çģ«èĬ±
    -0.08
    éĨĴ
    -0.08
    ucks
    -0.08
    çĶļèĩ³æĺ¯
    -0.08
    .Cmd
    -0.08
    uded
    -0.08
    形象
    -0.08
    æĬĢæľ¯åĴĮ
    -0.08
    æĹĮ
    -0.07
    POSITIVE LOGITS
    å¦Ĥä¸ĭ
    0.09
    åħ±çĶŁ
    0.09
    çĴŀ
    0.09
    ä¸Ńéĵģ
    0.09
    -peer
    0.09
    terr
    0.09
    åıĤåĬł
    0.09
    ä¸Ĭæľī
    0.09
    çĽ¸å¹²
    0.09
    antis
    0.08
    Activations Density 0.506%

    No Known Activations