© 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. 4399
    Prev
    Next
    INDEX
    Explanations

    street closures, blocked access

    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
    æ³»
    -0.09
    åİļåİļ
    -0.08
    éĶŃ
    -0.08
     DISPATCH
    -0.08
    ç°¿
    -0.08
    олов
    -0.08
    éķĢ
    -0.08
    廪
    -0.08
    ÑĢг
    -0.08
    oling
    -0.08
    POSITIVE LOGITS
    åłµ
    0.12
    åłµå¡ŀ
    0.12
    ãģĺ
    0.11
    å°ģéĶģ
    0.11
    åħ³éĹŃ
    0.10
    交éĢļ
    0.10
     closures
    0.10
    å°ģéĹŃ
    0.10
    çݯ
    0.09
    æѦåĬŁ
    0.09
    Activations Density 0.135%

    No Known Activations