© 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. 27603
    Prev
    Next
    INDEX
    Explanations

    intent and immense

    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
    ç¾¤å²Ľ
    -0.11
    媳
    -0.11
    ity
    -0.11
    ¿
    -0.10
    ãģıãĤĮ
    -0.10
    æ¼¾
    -0.09
    ä»Ģä¹ĪåİŁåĽł
    -0.09
    æŃ¤åŁºç¡Ģä¸Ĭ
    -0.09
    tek
    -0.09
    nt
    -0.09
    POSITIVE LOGITS
    ually
    0.13
    lessly
    0.13
    ened
    0.12
    uality
    0.11
    ify
    0.10
    cape
    0.10
    errupt
    0.10
    eners
    0.10
    ement
    0.10
    Åij
    0.10
    Activations Density 0.021%

    No Known Activations