© 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. 1503
    Prev
    Next
    INDEX
    Explanations

    qualities or descriptions

    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
    :both
    -0.23
     çĶŁåij½åij¨æľŁ
    -0.22
    ascus
    -0.22
    }elseif
    -0.21
    ?><
    -0.21
    åıĪ好åıĪ
    -0.21
    -vars
    -0.20
     beneficiation
    -0.20
    OLVE
    -0.20
    tá
    -0.20
    POSITIVE LOGITS
    *****/↵
    0.25
    åĭł
    0.25
    å¾Īå¤ļçݩ家
    0.25
    ****/↵
    0.24
    åıįèħIJåĢ¡å»ī
    0.23
    ç¾İåªĴ
    0.23
    个çĻ¾åĪĨ
    0.22
    åħĭæĢĿ
    0.22
     immune
    0.22
    ThanOr
    0.22
    Activations Density 3.132%

    No Known Activations