© 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. 52352
    Prev
    Next
    INDEX
    Explanations

    discussing comments

    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
    建åĨĽ
    -0.12
    éĩijå±±
    -0.10
    åı£åı·
    -0.10
    åĬŀåѦ
    -0.09
    åIJŁ
    -0.09
    æŁĶ软
    -0.09
    念
    -0.08
    isman
    -0.08
    .Document
    -0.08
    ä¸įæŃ»
    -0.08
    POSITIVE LOGITS
     comments
    0.14
    æĿ¡è¯Ħ论
    0.13
    ãĤ³ãĥ¡ãĥ³ãĥĪ
    0.13
    comments
    0.13
    .comments
    0.12
    è¯Ħ论
    0.12
     ëĮĵê¸Ģ
    0.12
    comment
    0.11
     Comment
    0.11
    çķĻè¨Ģ
    0.11
    Activations Density 0.141%

    No Known Activations