© 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. 20119
    Prev
    Next
    INDEX
    Explanations

    telecommunications

    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
    ledge
    -0.09
    ween
    -0.09
    itan
    -0.09
    éªĽ
    -0.09
    uke
    -0.08
    plate
    -0.08
    pler
    -0.08
    zej
    -0.08
    seys
    -0.08
     Dillon
    -0.08
    POSITIVE LOGITS
    edException
    0.10
    aire
    0.10
    æģŃåĸľ
    0.10
    edList
    0.09
    ulario
    0.09
    åIJ¦è®¤
    0.09
    íĻĪ
    0.09
    ä¸įéĢļ
    0.09
    reira
    0.09
    enia
    0.09
    Activations Density 0.003%

    No Known Activations