© 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. 10873
    Prev
    Next
    INDEX
    Explanations

    greeting or message

    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
    æİĪäºĪ
    -0.09
    åIJ¹
    -0.09
    urally
    -0.09
     Cath
    -0.09
    åīįçŀ»
    -0.08
    åĽŀå¿Ĩ
    -0.08
    å°±çŁ¥éģĵ
    -0.08
    _CRC
    -0.08
    utos
    -0.08
     suspend
    -0.08
    POSITIVE LOGITS
     message
    0.13
    æłĩè¯Ń
    0.11
    å¥ļ
    0.10
    message
    0.10
    éĹ®åĢĻ
    0.09
    Message
    0.09
    åĢĴæĺ¯
    0.09
    _message
    0.09
     messages
    0.08
    åı£åı·
    0.08
    Activations Density 0.099%

    No Known Activations