© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 9007
    Prev
    Next
    INDEX
    Explanations

    caught doing something unethical or illegal

    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
    æĿijåŃIJ
    -0.09
    /fs
    -0.09
    .getLength
    -0.09
    .getUserName
    -0.08
    _ALARM
    -0.08
    .Engine
    -0.08
    -priced
    -0.08
    æĦıè§ģåıįé¦Ī
    -0.08
    ä»ĸèĩªå·±
    -0.08
    èģŀ
    -0.08
    POSITIVE LOGITS
    沧
    0.10
    ä½¾
    0.09
    ses
    0.09
    çĻ¾èĬ±
    0.09
    åģļçļĦäºĭæĥħ
    0.09
    æı¡
    0.09
    çĢij
    0.09
    仪
    0.08
    è¡Įèµ°
    0.08
    erg
    0.08
    Activations Density 0.021%

    No Known Activations