© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 22192
    Prev
    Next
    INDEX
    Explanations

    Hoboken

    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
    碰
    -0.11
    æĽ¾ä»»
    -0.10
    çľĩ
    -0.09
    æĸŃè£Ĥ
    -0.09
    é»ĺå¥ij
    -0.09
    çĽijäºĭä¼ļ
    -0.09
    ãģ»ãģ©
    -0.08
    å¤ĦåĪĨ
    -0.08
    ivals
    -0.08
    æīĵçIJĥ
    -0.08
    POSITIVE LOGITS
    èĢĹ
    0.09
    NST
    0.09
    änger
    0.09
    _Execute
    0.09
    è¿ĽäºĨ
    0.09
    iden
    0.08
    ieber
    0.08
    getContent
    0.08
    anse
    0.08
    лик
    0.08
    Activations Density 0.003%

    No Known Activations