© 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. 20332
    Prev
    Next
    INDEX
    Explanations

    fun activities and experiences

    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
    ague
    -0.10
    è°Īè°Ī
    -0.08
    æѦæŀĹ
    -0.08
    anger
    -0.08
    ä½Ĩ她
    -0.08
    åłĻ
    -0.08
    çĢ¼
    -0.08
    çķıæĥ§
    -0.08
    lund
    -0.08
    èĻIJ
    -0.08
    POSITIVE LOGITS
    èĬĴ
    0.10
     Beard
    0.10
    诣
    0.10
    ä¸İåıijå±ķ
    0.10
    诮
    0.09
    èĭĮ
    0.09
    åĴĮåıijå±ķ
    0.09
    -filled
    0.09
    çļĦåIJĮæŶ
    0.08
    åı£åı·
    0.08
    Activations Density 0.013%

    No Known Activations