© 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. 1830
    Prev
    Next
    INDEX
    Explanations

    numbers and codes

    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
    лад
    -0.20
    @Setter
    -0.20
    娱ä¹IJå¹³åı°
    -0.19
     OnCollision
    -0.19
     tslint
    -0.19
     ut
    -0.18
     beÄŁen
    -0.18
     télécharg
    -0.18
    /animate
    -0.18
    åĿı
    -0.18
    POSITIVE LOGITS
    acerb
    0.25
    udiantes
    0.24
    /Dk
    0.23
    paralleled
    0.22
    aghetti
    0.22
    occan
    0.22
    tees
    0.22
     porr
    0.21
    redi
    0.21
     practition
    0.21
    Activations Density 0.006%

    No Known Activations