© 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-CHAT-65K
    7. 46498
    Prev
    Next
    INDEX
    Explanations

    sexually suggestive or assistant

    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/lmsys/matryoshka/k-100
    Prompts (Dashboard)
    16,384 prompts, 192 tokens each
    Dataset (Dashboard)
    chanind/lmsys-chat-1m-qwen-2.5
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    tabpanel
    -0.24
    åĸĨ
    -0.23
     RaisePropertyChanged
    -0.20
    ide
    -0.20
     chac
    -0.20
    noticed
    -0.20
    å¯IJ
    -0.20
    uss
    -0.20
     OnPropertyChanged
    -0.20
    æĸĩæ¡Ī
    -0.19
    POSITIVE LOGITS
    :<?
    0.25
    ,eg
    0.25
    ****/↵
    0.24
    reator
    0.23
    anmar
    0.23
    -valu
    0.23
    ɵ
    0.22
    pisa
    0.22
    theid
    0.22
    >\<
    0.22
    Activations Density 0.001%

    No Known Activations