© 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. 21009
    Prev
    Next
    INDEX
    Explanations

    dissect

    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
    iken
    -0.09
    eração
    -0.09
    fur
    -0.09
    доб
    -0.09
    ÑĥÑīеÑģÑĤв
    -0.08
    ÙĬات
    -0.08
    ä¾Ī
    -0.08
    aurus
    -0.08
    inals
    -0.08
    erk
    -0.08
    POSITIVE LOGITS
    åīĸæŀIJ
    0.09
    rame
    0.09
    entifier
    0.09
    å¦Ĥä½ķçľĭå¾ħ
    0.09
    mania
    0.09
    ian
    0.09
    ä¸Ģçķª
    0.09
    åįĬå²Ľ
    0.08
    RIA
    0.08
    槽
    0.08
    Activations Density 0.023%

    No Known Activations