© 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. 54919
    Prev
    Next
    INDEX
    Explanations

    intervene or attacked abroad

    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
    ook
    -0.09
    æļĸ
    -0.09
     ltd
    -0.08
    çĤĢ
    -0.08
    ä¸Ńè¶ħ
    -0.08
     Spiral
    -0.08
    aret
    -0.08
    äº
    -0.08
    æīįæĺ¯çľŁæŃ£
    -0.08
     Needle
    -0.08
    POSITIVE LOGITS
    å¹²é¢Ħ
    0.11
    å¹²æ¶ī
    0.10
    å¿į
    0.10
    é¼ĵåĬ±
    0.09
    æī¶æĮģ
    0.09
    æī¶
    0.09
    èĬ±æł·
    0.09
     famine
    0.09
    ñe
    0.09
    èĪĮå°ĸ
    0.09
    Activations Density 0.125%

    No Known Activations