© 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. 30406
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    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
    ãģİ
    -0.10
    窨
    -0.09
    èľĪ
    -0.08
    itational
    -0.08
    ifax
    -0.08
    esk
    -0.08
    -scalable
    -0.08
    enn
    -0.08
    inton
    -0.08
    åĵļ
    -0.08
    POSITIVE LOGITS
    oon
    0.10
    ype
    0.10
    rix
    0.10
    åĬŁå¤«
    0.09
    arra
    0.09
    sis
    0.09
    tes
    0.09
    åĪĨåĮº
    0.08
    cheid
    0.08
    reuse
    0.08
    Activations Density 0.000%

    No Known Activations