© 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. Qwen3.5-4B
    5. 15-RES-MATRYOSHKA-65K
    7. 18499
    Prev
    Next
    INDEX
    Explanations

    physical locations or objects

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    decoderesearch/qwen-3.5-saes/qwen-3.5-4b
    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
    aglia
    -0.06
    swick
    -0.06
    æ°Ľ
    -0.06
    iegen
    -0.06
     anthrop
    -0.06
    ÙĦب
    -0.05
     unconditional
    -0.05
    ØŃت
    -0.05
     ì¹ľ
    -0.05
     CLA
    -0.05
    POSITIVE LOGITS
    si
    0.06
     ÐŀÑģÑĤа
    0.05
    ymes
    0.05
     deleted
    0.05
    .dump
    0.05
     dumped
    0.05
    alih
    0.05
    kar
    0.05
    èĢĮéĤ£äºĽ
    0.05
    Form
    0.05
    Activations Density 0.010%

    No Known Activations