© 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. Qwen2.5-7B-IT
    5. 20-MATRYOSHKA-65K
    7. 971
    Prev
    Next
    INDEX
    Explanations

    References

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    chanind/qwen2.5-7B-it-layer-20-saes/pile/matryoshka/k-100
    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
    ä¸ī大éĺ¶æ®µ
    -0.25
    OLON
    -0.20
    incinnati
    -0.20
    åĹIJ
    -0.20
     ="";↵
    -0.20
    :numel
    -0.19
    ãģĮå§ĭãģ¾
    -0.19
    åĶ·
    -0.19
    Opcode
    -0.19
    retweeted
    -0.19
    POSITIVE LOGITS
    :
    0.37
    ï¼ļ
    0.31
    :↵
    0.30
    ï¼ļ↵
    0.26
    :↵↵
    0.25
    :č↵
    0.24
    :,
    0.23
    :m
    0.23
    /WebAPI
    0.23
    :[
    0.22
    Activations Density 2.396%

    No Known Activations