© 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. 22071
    Prev
    Next
    INDEX
    Explanations

    as a result

    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
    anyl
    -0.10
    TEL
    -0.09
    alyzed
    -0.09
    å«Į
    -0.09
    çĢij
    -0.08
    èĿĩ
    -0.08
    ç»ĨåĪĻ
    -0.08
    é¢Ĩ
    -0.08
    æīĩ
    -0.08
     Mare
    -0.08
    POSITIVE LOGITS
    åĽłæѤ
    0.29
     therefore
    0.26
    åĽłèĢĮ
    0.23
     поÑįÑĤомÑĥ
    0.22
    ä¹ŁåĽłæѤ
    0.21
    æį®æѤ
    0.19
     donc
    0.18
     thus
    0.18
    Therefore
    0.18
     quindi
    0.18
    Activations Density 0.101%

    No Known Activations