© 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. 18805
    Prev
    Next
    INDEX
    Explanations

    poisoning and overdose

    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
    åıĺå¹»
    -0.09
    cratch
    -0.08
    ç»ĨèıĮ
    -0.08
    åĸľå¥½
    -0.08
    çĸ¾çĹħ
    -0.08
     chip
    -0.08
    SHIP
    -0.08
    çĪ±å¥½
    -0.08
     preferences
    -0.08
    _preferences
    -0.08
    POSITIVE LOGITS
     overdose
    0.11
    æĢ¥æķij
    0.11
    åIJĥäºı
    0.10
     poisoning
    0.10
    ä¸Ńå¿ĥ
    0.10
    èħĭ
    0.09
    ä¸Ńæ¯Ĵ
    0.09
    åĩłä¹İæĺ¯
    0.09
    æķijåĬ©
    0.09
    èį»
    0.09
    Activations Density 0.236%

    No Known Activations