© 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. 17385
    Prev
    Next
    INDEX
    Explanations

    carbon compounds and cycles

    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
    urat
    -0.10
    enga
    -0.09
    ges
    -0.09
    ãģĵãģ¨
    -0.09
    ÖĤ
    -0.09
    ertz
    -0.09
    ingo
    -0.09
    бол
    -0.09
    pee
    -0.09
    åīįæīĢ
    -0.09
    POSITIVE LOGITS
    aceous
    0.17
     dioxide
    0.16
    azzi
    0.10
    ized
    0.10
    ization
    0.10
    ium
    0.10
    ioxide
    0.09
    å°±æĺ¯åĽłä¸º
    0.09
    çĸ½
    0.09
    å¤ļåľ°
    0.09
    Activations Density 0.042%

    No Known Activations