© 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. Qwen2.5-7B-IT
    5. 20-MATRYOSHKA-65K
    7. 309
    Prev
    Next
    INDEX
    Explanations

    code and comments

    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
    .createTextNode
    -0.25
    shaw
    -0.22
    -provider
    -0.22
    lobs
    -0.21
    .StObject
    -0.21
    :'.$
    -0.20
    .FILL
    -0.20
    (Roles
    -0.20
    omat
    -0.20
    ldr
    -0.19
    POSITIVE LOGITS
    #ab
    0.26
    abcdefghijklmnop
    0.22
    ÅĤow
    0.20
    (parseFloat
    0.19
     Sleeve
    0.19
    kü
    0.18
    #ac
    0.18
    #ga
    0.18
    	dist
    0.18
    anuts
    0.18
    Activations Density 0.001%

    No Known Activations