© 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. 19653
    Prev
    Next
    INDEX
    Explanations

    chemistry education and research

    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
    ¹
    -0.09
    hani
    -0.09
    aire
    -0.09
    iture
    -0.09
     ведÑĮ
    -0.09
    ombre
    -0.09
    owing
    -0.08
    ame
    -0.08
    attery
    -0.08
    amas
    -0.08
    POSITIVE LOGITS
    åĭĥåĭĥ
    0.13
    çĿ¬
    0.11
    åįģ足
    0.09
     ë¶Ī구íķĺê³ł
    0.09
    soever
    0.09
    sources
    0.09
    ÙĨÙĬÙĨ
    0.09
    è¿©
    0.09
    ically
    0.09
    goo
    0.09
    Activations Density 0.033%

    No Known Activations