© 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. 1379
    Prev
    Next
    INDEX
    Explanations

    reason or condition

    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
     (~(
    -0.24
     Basement
    -0.24
    ();)
    -0.23
    nowrap
    -0.23
     jihadists
    -0.23
    ’B
    -0.23
     Hindered
    -0.23
     Washer
    -0.22
     RequestMethod
    -0.22
     dequeueReusableCellWithIdentifier
    -0.22
    POSITIVE LOGITS
     there
    0.59
     it
    0.46
    there
    0.43
     they
    0.42
     we
    0.40
     the
    0.36
     There
    0.31
     you
    0.29
     each
    0.28
     this
    0.28
    Activations Density 3.866%

    No Known Activations