© 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. 38814
    Prev
    Next
    INDEX
    Explanations

    life sentence prison

    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
    å¾ģ
    -0.09
    è£Ļ
    -0.09
    æıª
    -0.09
     капиÑĤ
    -0.09
    æľīä¸Ģ次
    -0.09
    erview
    -0.09
    æłijåı¶
    -0.09
    éĹ¾
    -0.09
    èĥľè´Ł
    -0.09
    ãĤ¤ãĥ¤
    -0.09
    POSITIVE LOGITS
    æľīæľŁå¾ĴåĪij
    0.10
    åĽ´å¢Ļ
    0.10
    çĽijçĭ±
    0.10
    å°ijåIJĥ
    0.09
    俵
    0.09
    maj
    0.09
     jail
    0.09
     prison
    0.08
    çĭ±
    0.08
    elter
    0.08
    Activations Density 0.106%

    No Known Activations