© 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. 2701
    Prev
    Next
    INDEX
    Explanations

    Names and entities

    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
    <fieldset
    -0.23
    åıĪ好åıĪå¿«
    -0.20
    elsey
    -0.20
    ä¸ĩ亿åħĥ
    -0.20
    èĥ¤
    -0.19
     numel
    -0.19
    æ¼ł
    -0.18
    æķĻèĤ²åŁ¹è®Ń
    -0.18
    èĶ½
    -0.18
    multiline
    -0.18
    POSITIVE LOGITS
     Äijá»±
    0.25
    leanor
    0.24
    entiful
    0.21
    ;"><?
    0.20
     UITableViewController
    0.20
     erotisch
    0.20
    rary
    0.20
    skirts
    0.20
    printStats
    0.20
     CDDL
    0.19
    Activations Density 0.001%

    No Known Activations