© 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. 9965
    Prev
    Next
    INDEX
    Explanations

    guy or guys

    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
    ãģ£ãģįãĤĬ
    -0.11
    æĪIJè´¥
    -0.10
    ãģĦãģĨ
    -0.10
    еб
    -0.10
    .Messaging
    -0.10
    à¹Ĥลà¸ģ
    -0.09
    çĹĩ
    -0.09
    ixe
    -0.09
    HEME
    -0.09
    ECH
    -0.09
    POSITIVE LOGITS
    ðŁı»
    0.11
    们çļĦ
    0.11
    ðŁı¼
    0.10
    们éĥ½
    0.10
    ÅĤÄĻ
    0.09
    iliar
    0.09
    ·
    0.09
    teen
    0.08
    åĢij
    0.08
     hundred
    0.08
    Activations Density 0.014%

    No Known Activations