© 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. 2191
    Prev
    Next
    INDEX
    Explanations

    coast to coast

    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
    大åħ¨
    -0.09
    çģ«çĦ°
    -0.08
    åĽ½ç«ĭ
    -0.08
    ewire
    -0.08
    éĬ
    -0.08
    agger
    -0.08
    aka
    -0.08
    ober
    -0.08
    akan
    -0.08
    amar
    -0.08
    POSITIVE LOGITS
    ä¸į说
    0.10
    æݥ管
    0.10
     VID
    0.09
    ä¸įåĪĨ
    0.09
    è¡£
    0.09
    alyzer
    0.09
    å§Ķå®£ä¼łéĥ¨
    0.09
    rup
    0.09
    .LENGTH
    0.09
    åĵ¥ä»¬
    0.08
    Activations Density 0.007%

    No Known Activations