© 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. 61120
    Prev
    Next
    INDEX
    Explanations

    among

    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
    ä¸Ģèīĺ
    -0.09
    åħ±æľī
    -0.09
    old
    -0.08
    éĽĨä¸Ń
    -0.08
    æĬ¹
    -0.08
    æł·çļĦ
    -0.08
    ikes
    -0.08
    IKE
    -0.08
    eds
    -0.08
    ike
    -0.08
    POSITIVE LOGITS
    ä¸įä¸ĭ
    0.10
    çĿĢä»ĸ
    0.10
    itsu
    0.10
    åĮĸè¿Ľç¨ĭ
    0.10
    éĺħ读åħ¨æĸĩ
    0.09
    stamp
    0.09
    ç¿Ĵæħ£
    0.09
    åİŁåĽłæĺ¯
    0.09
    亿ä¸ĩ
    0.09
    æ¯Ķè¾ĥé«ĺ
    0.09
    Activations Density 0.033%

    No Known Activations