© 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. 57062
    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
    atories
    -0.09
    åĩºæ±Ĺ
    -0.09
    wel
    -0.09
    دس
    -0.09
    ective
    -0.09
    个å¤ļ
    -0.09
    æıIJæĹ©
    -0.09
    åĻ±
    -0.09
    伪è£ħ
    -0.09
    ected
    -0.08
    POSITIVE LOGITS
    ä¸įèĪį
    0.09
     Lump
    0.09
    real
    0.09
    .dds
    0.09
    aida
    0.08
    .getDouble
    0.08
    elts
    0.08
    èı©æıIJ
    0.08
    bon
    0.08
    ãģ«ãģĤãĤĭ
    0.08
    Activations Density 0.006%

    No Known Activations