© 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. 2682
    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
    IRTUAL
    -0.27
     Gorgeous
    -0.24
    åħ¶å®ĥéĹ®é¢ĺ
    -0.20
     télécharg
    -0.20
    inus
    -0.19
    (Print
    -0.19
    éĶ
    -0.19
    on
    -0.18
    VERN
    -0.18
    åĻ±
    -0.18
    POSITIVE LOGITS
     çĶŁåij½åij¨æľŁ
    0.27
    çĸ¥
    0.24
    oste
    0.23
     rekl
    0.23
    esz
    0.23
     èĩªåĬ¨çĶŁæĪIJ
    0.23
    å¦Ĭ
    0.23
    puties
    0.23
    utomation
    0.22
    hiba
    0.22
    Activations Density 0.000%

    No Known Activations