© 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. 2486
    Prev
    Next
    INDEX
    Explanations

    place name parts

    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
    avorites
    -0.25
    acades
    -0.22
    :"-
    -0.21
    icontrol
    -0.21
    /MPL
    -0.21
    anyahu
    -0.20
    },č↵č↵
    -0.20
    [now
    -0.20
     public
    -0.20
    CHOOL
    -0.20
    POSITIVE LOGITS
    åĨĪ
    0.22
    arrière
    0.21
    sville
    0.21
    ä½»
    0.19
    æģĭ人
    0.19
    åı£
    0.19
     ])->
    0.18
    ulerAngles
    0.18
     Angeles
    0.18
    antan
    0.18
    Activations Density 0.703%

    No Known Activations