© 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. 54905
    Prev
    Next
    INDEX
    Explanations

    transcripts and speech

    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
    称ä¹ĭ
    -0.11
    å·¯
    -0.10
    iban
    -0.10
    _PTR
    -0.10
    éĿĵ
    -0.10
    å¹´åĨħ
    -0.09
    ä»ĸçŁ¥éģĵ
    -0.09
    çŁ¥å·±
    -0.09
    稳妥
    -0.09
    羨
    -0.08
    POSITIVE LOGITS
    å½ķéŁ³
    0.12
     transcript
    0.12
     transcripts
    0.11
     Speech
    0.10
     speech
    0.10
    æĭ·
    0.10
    è¯ŃéŁ³
    0.09
     speeches
    0.09
    Speech
    0.09
    pond
    0.09
    Activations Density 0.123%

    No Known Activations