© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen2.5-7B-IT
    5. 20-MATRYOSHKA-65K
    7. 3548
    Prev
    Next
    INDEX
    Explanations

    structured information

    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
    \Doctrine
    -0.20
    Disappear
    -0.19
    -redux
    -0.19
    ramento
    -0.19
    ByExample
    -0.18
    å¨ģå°Ķ
    -0.18
    >(*
    -0.18
    inded
    -0.18
    对她
    -0.18
    åīĬå¼±
    -0.18
    POSITIVE LOGITS
    )__
    0.24
    @update
    0.24
    嫱
    0.23
    åľ¨è¿ĩæ¸¡æľŁ
    0.23
    >manual
    0.22
    acades
    0.22
    ?family
    0.22
    oÄŁlu
    0.21
    讧
    0.21
    uite
    0.21
    Activations Density 0.006%

    No Known Activations