© 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. 38735
    Prev
    Next
    INDEX
    Explanations

    telnet, telephone, telstra, telugu

    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
    plied
    -0.10
    带头人
    -0.09
    ohl
    -0.09
    Äħ
    -0.08
    als
    -0.08
    æŬ
    -0.08
    OUR
    -0.08
    æĬĬæı¡
    -0.08
    ality
    -0.08
    åĮĸçļĦ
    -0.08
    POSITIVE LOGITS
    inger
    0.09
    .fm
    0.09
    rese
    0.09
    ataire
    0.09
    ặng
    0.09
    ipt
    0.09
    tsy
    0.09
    éfono
    0.09
    -vous
    0.09
    ãģªãģĮãĤī
    0.09
    Activations Density 0.015%

    No Known Activations