© 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. 3935
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    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
    '].'/
    -0.24
    usterity
    -0.23
    muÅŁ
    -0.21
    oste
    -0.20
    .AutoScaleMode
    -0.19
    .PERMISSION
    -0.19
    ='".
    -0.19
    tokenId
    -0.18
    _LITERAL
    -0.18
     careg
    -0.18
    POSITIVE LOGITS
    .handleSubmit
    0.27
    .handleChange
    0.21
    enheim
    0.20
    ENTIC
    0.20
    imageView
    0.19
    ìĨį
    0.19
    icensing
    0.19
     enth
    0.19
     Feinstein
    0.19
    isex
    0.18
    Activations Density 0.002%

    No Known Activations