© 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. 19787
    Prev
    Next
    INDEX
    Explanations

    Jacksonville

    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
    å´Ĩ
    -0.09
    aceous
    -0.09
     entire
    -0.09
     khÄĥn
    -0.09
    累累
    -0.09
    å¸ĺ
    -0.09
    åĩłåĪĨ
    -0.08
    ocracy
    -0.08
    äºį
    -0.08
    ensch
    -0.08
    POSITIVE LOGITS
    èĤ¤
    0.10
    é²ľæĺİ
    0.10
    0.10
    ously
    0.10
    hin
    0.09
    odia
    0.08
    utron
    0.08
    æ³½
    0.08
    omat
    0.08
    úa
    0.08
    Activations Density 0.016%

    No Known Activations