© 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. 65
    Prev
    Next
    INDEX
    Explanations

    unusual characters

    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
    JsonValue
    -0.20
    	DECLARE
    -0.19
    ç¾İåªĴ
    -0.19
    aoke
    -0.19
    糧
    -0.18
    tle
    -0.18
    enzie
    -0.18
    perfil
    -0.18
     hairy
    -0.18
    دÙĬØ©
    -0.18
    POSITIVE LOGITS
    )$_
    0.27
    cej
    0.24
    Ê°
    0.22
    iesen
    0.22
    =-=-
    0.21
    orca
    0.20
    ylko
    0.20
    æĹłè®ºæĺ¯åħ¶
    0.20
    plemented
    0.19
    TERNAL
    0.19
    Activations Density 0.001%

    No Known Activations