© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen2.5-7B-IT
    5. 20-MATRYOSHKA-65K
    7. 1244
    Prev
    Next
    INDEX
    Explanations

    error messages

    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
     Rencontre
    -0.25
    offsetof
    -0.24
     STDCALL
    -0.23
    ;;;;;;;;
    -0.23
     FUCK
    -0.23
    setattr
    -0.23
     **/č↵
    -0.22
     unterstützen
    -0.21
    fillType
    -0.21
     horr
    -0.21
    POSITIVE LOGITS
    è¿Ļ个èģĮä¸ļ
    0.25
     sublic
    0.24
    æ¡İ
    0.23
    æºĺ
    0.21
    没æľīä»»ä½ķ
    0.21
     foyer
    0.21
    ();?>
    0.20
     unrecognized
    0.20
    家åĸ»
    0.20
    <fieldset
    0.20
    Activations Density 2.377%

    No Known Activations