© 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. Qwen3.5-4B
    5. 15-RES-MATRYOSHKA-65K
    7. 18283
    Prev
    Next
    INDEX
    Explanations

    bigger, smaller, larger, lesser

    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
     تÙĨد
    -0.06
    åħ¬ç§ģ
    -0.06
    pst
    -0.05
    ivalent
    -0.05
    大å¹ħä¸ĭéĻį
    -0.05
    iga
    -0.05
    æĬĢæľ¯æĢ§
    -0.05
    软硬
    -0.05
    imag
    -0.05
    ×¢×Ļ
    -0.05
    POSITIVE LOGITS
    ç©·
    0.06
     parazit
    0.06
    æ·±éĢł
    0.06
    æĹłæ¯Ĵ
    0.06
     mult
    0.05
    æĹłè¯Ń
    0.05
     Simply
    0.05
     orphan
    0.05
    أس
    0.05
     hung
    0.05
    Activations Density 0.039%

    No Known Activations