© 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. 63053
    Prev
    Next
    INDEX
    Explanations

    loud vocalizations

    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
    ally
    -0.09
    uilt
    -0.09
    éĤĪ
    -0.09
    æĩĭ
    -0.09
    lec
    -0.09
    ycl
    -0.09
    raig
    -0.09
    à¸Ńà¸Ķ
    -0.09
    uong
    -0.08
    aten
    -0.08
    POSITIVE LOGITS
    æ§Ľ
    0.12
    /rfc
    0.10
    érie
    0.10
    oused
    0.10
    èµ·æĿ¥äºĨ
    0.09
     vá»įng
    0.09
    ä¸Ģ声
    0.09
    èµ·æĿ¥
    0.09
    åĽ½éĻħæľºåľº
    0.09
    æĢ§å¼º
    0.09
    Activations Density 0.004%

    No Known Activations