© 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. 2424
    Prev
    Next
    INDEX
    Explanations

    -

    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
    è¯ĭ
    -0.23
     bordel
    -0.21
    kes
    -0.20
     Pai
    -0.20
     اÙĦÙĦج
    -0.19
    probe
    -0.18
    vanized
    -0.18
     }*/↵↵
    -0.18
     bindActionCreators
    -0.18
    améli
    -0.18
    POSITIVE LOGITS
     CDDL
    0.22
    使çĶ¨èĢħæĪĸ
    0.20
    ormsg
    0.20
    Salir
    0.20
    PWD
    0.20
    gency
    0.19
     Emanuel
    0.19
    uvw
    0.19
    æµĥ
    0.18
    ierz
    0.18
    Activations Density 0.015%

    No Known Activations