© 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. 2099
    Prev
    Next
    INDEX
    Explanations

    safe and shelter

    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
    éķ¿çŁŃ
    -0.11
    æݥ轨
    -0.10
    å§Ĺ
    -0.09
    ;++
    -0.09
    æŃ¥åħ¥
    -0.09
    æĢħ
    -0.09
    墨西
    -0.09
    åĿĬ
    -0.09
    elor
    -0.09
    rub
    -0.08
    POSITIVE LOGITS
    å®īåħ¨
    0.19
    躲éģ¿
    0.17
    躲
    0.17
     safety
    0.16
    åºĩ
    0.16
     safe
    0.16
    à¸Ľà¸¥à¸Ńà¸Ķ
    0.16
    å®īåħ¨æĢ§
    0.16
    éģ¿
    0.16
    safe
    0.15
    Activations Density 0.065%

    No Known Activations