© 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. 49769
    Prev
    Next
    INDEX
    Explanations

    ring

    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
    åIJ¸
    -0.09
    uggage
    -0.09
    èľĤ
    -0.09
    åħľ
    -0.08
    ç»ĩ
    -0.08
    ç§ī
    -0.08
    è¡£
    -0.08
    åī¯å±Ģéķ¿
    -0.08
    æĿŃ
    -0.08
    AGER
    -0.08
    POSITIVE LOGITS
    éķĮ
    0.10
     rings
    0.10
    -ring
    0.09
    Ring
    0.09
     Ring
    0.09
    å°Ĩ士
    0.08
    ardi
    0.08
    kees
    0.08
    æĪĴæĮĩ
    0.08
     ring
    0.08
    Activations Density 0.020%

    No Known Activations