© 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. Qwen3-8B
    5. 18-RESID-BATCHTOPK-65K__L0-80
    7. 154
    Prev
    Next
    INDEX
    Explanations

    split, divide, into pieces

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    adamkarvonen/qwen3-8b-saes/saes_Qwen_Qwen3-8B_batch_top_k/resid_post_layer_18
    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
    Tac
    -0.24
     ê¶
    -0.22
     Axis
    -0.21
     overturned
    -0.21
    è¿Ļ个è¡Įä¸ļ
    -0.21
    Inspector
    -0.21
    äºĤ
    -0.21
     usher
    -0.21
     Embedded
    -0.20
     ÐĴлад
    -0.20
    POSITIVE LOGITS
     manageable
    0.35
    åĪĨ解
    0.35
     smaller
    0.34
    æŃ¥éª¤
    0.31
     steps
    0.31
    æĭĨ
    0.30
     splits
    0.29
    ä¸ĢæŃ¥ä¸ĢæŃ¥
    0.29
     pieces
    0.29
     split
    0.29
    Activations Density 0.092%

    No Known Activations