© 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. 38774
    Prev
    Next
    INDEX
    Explanations

    held captive or prisoner

    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
    kok
    -0.10
    tern
    -0.09
    .appspot
    -0.09
    åѤåĦ¿
    -0.09
    çĵ¯
    -0.08
    å¹Ħ
    -0.08
    .tiles
    -0.08
    ä¸Ŀ绸
    -0.08
    æ²»å®ī
    -0.08
    quiv
    -0.08
    POSITIVE LOGITS
    è¡Įéķ¿
    0.11
    éĺħ读åħ¨æĸĩ
    0.10
    媵
    0.09
    çľĭä¸įè§ģ
    0.09
    som
    0.09
    Neal
    0.08
    å¤§éĽ¨
    0.08
    å¾Ģè¿Ķ
    0.08
    -ng
    0.08
    portal
    0.08
    Activations Density 0.011%

    No Known Activations