© 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. 62976
    Prev
    Next
    INDEX
    Explanations

    this topic

    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
    suming
    -0.11
    PTY
    -0.10
    å¹ķ
    -0.10
    æ´¾
    -0.09
    å§ĭ
    -0.09
    ahu
    -0.09
    ided
    -0.09
    æĴŀåĩ»
    -0.09
    ael
    -0.08
    boa
    -0.08
    POSITIVE LOGITS
     matter
    0.10
    äºĭ项
    0.10
     matters
    0.09
    è¿Ļ件äºĭæĥħ
    0.09
     topic
    0.09
     regard
    0.09
    è¿Ļ个éĹ®é¢ĺ
    0.09
    è¿Ļ件äºĭ
    0.09
    -topic
    0.09
    _TOPIC
    0.09
    Activations Density 0.061%

    No Known Activations