© 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. 30898
    Prev
    Next
    INDEX
    Explanations

    addiction, dependent, addictive

    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
    _BP
    -0.10
    ertz
    -0.09
     اÙĦجز
    -0.09
    éĵİ
    -0.09
    溯
    -0.09
    å¤§éĽ¨
    -0.09
    æĶ¾è¿ĩ
    -0.09
    ä¸īå±Ĥ
    -0.08
    _UC
    -0.08
    cook
    -0.08
    POSITIVE LOGITS
     addictive
    0.15
    çĺ¾
    0.14
     addiction
    0.13
     addicted
    0.13
     addict
    0.11
     compuls
    0.11
    æ²īè¿·
    0.11
     Addiction
    0.11
    åĹľ
    0.10
    çĹ´è¿·
    0.10
    Activations Density 0.043%

    No Known Activations