© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 36561
    Prev
    Next
    INDEX
    Explanations

    seal or sealing

    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
    æİı
    -0.09
    èĬĴ
    -0.09
    .Branch
    -0.09
    ç¿¡
    -0.09
    undi
    -0.09
    çŁĽçĽ¾
    -0.09
    tal
    -0.08
    avel
    -0.08
    æIJħ
    -0.08
    åĽłæŀľ
    -0.08
    POSITIVE LOGITS
    å¯Ĩå°ģ
    0.14
     Leakage
    0.11
     seal
    0.11
     seals
    0.11
     sealing
    0.11
    æ³Ħéľ²
    0.10
     leakage
    0.10
    GIN
    0.10
    æ³Ħæ¼ı
    0.10
    ä¿Ŀéļľ
    0.10
    Activations Density 0.099%

    No Known Activations