© 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. 3917
    Prev
    Next
    INDEX
    Explanations

    sqrt

    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
    ðŁĻĤ
    -0.22
     mHandler
    -0.21
    åı£æ°Ķ
    -0.20
    anitize
    -0.20
     Inflate
    -0.19
    MBER
    -0.19
    ++++++++++++++++
    -0.19
    -www
    -0.19
    çĸ³
    -0.19
    ì°½
    -0.19
    POSITIVE LOGITS
    thinkable
    0.26
    paralleled
    0.23
    fwrite
    0.22
    eworthy
    0.21
    个çĻ¾åĪĨ
    0.20
     ><?
    0.20
    è¯ł
    0.20
    iage
    0.20
    forgettable
    0.20
     overwhel
    0.19
    Activations Density 0.008%

    No Known Activations