© 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. 54211
    Prev
    Next
    INDEX
    Explanations

    location or state of being

    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
    飽
    -0.10
    åIJł
    -0.09
    ä»ĩ
    -0.09
    饱
    -0.08
    çĤľ
    -0.08
    æĭĵå±ķ
    -0.08
    æĸ°ä¸Ģè½®
    -0.08
     instructor
    -0.08
    æıŃå¼Ģ
    -0.08
    BD
    -0.08
    POSITIVE LOGITS
    åľ¨çİ°åľº
    0.15
     presence
    0.12
    çİ°åľº
    0.12
    çı¾åł´
    0.12
    Presence
    0.12
    亲身
    0.11
    åıĤåĬłäºĨ
    0.11
    presence
    0.11
    æ´»åĬ¨çİ°åľº
    0.11
    亲
    0.10
    Activations Density 0.089%

    No Known Activations