© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 8479
    Prev
    Next
    INDEX
    Explanations

    looking for / forward to / into

    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
    .GetItem
    -0.09
     Ñģобой
    -0.09
    пан
    -0.08
     FLT
    -0.08
    nad
    -0.08
    çĭĤ
    -0.08
    ä¸įå®Į
    -0.08
    mates
    -0.08
     ÑĩаÑģÑĤÑĮ
    -0.08
    第ä¸Ģ次
    -0.08
    POSITIVE LOGITS
    ondo
    0.10
    好äºĨ
    0.10
    -eyed
    0.09
     Abe
    0.09
    bons
    0.09
    ither
    0.09
    èĸĩ
    0.09
    bens
    0.09
    èĢĥéªĮ
    0.08
    éĮ¾
    0.08
    Activations Density 0.026%

    No Known Activations