© 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. 5655
    Prev
    Next
    INDEX
    Explanations

    suffix `ment` or `ed` or `ing`

    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
    born
    -0.09
    ulos
    -0.09
    å²±
    -0.09
    们çļĦ
    -0.09
    UpDown
    -0.09
    itas
    -0.09
    ulously
    -0.09
    heads
    -0.09
    ocre
    -0.08
     налогов
    -0.08
    POSITIVE LOGITS
    ment
    0.16
    ered
    0.11
    ded
    0.10
    ted
    0.10
    uration
    0.10
    agement
    0.10
    ioned
    0.10
    ting
    0.09
    ments
    0.09
    å·¥ä½ľç»Ħ
    0.09
    Activations Density 0.058%

    No Known Activations