© 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. 20567
    Prev
    Next
    INDEX
    Explanations

    cellspacing="

    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
     hete
    -0.06
     dominan
    -0.06
    ÙĩØ©
    -0.05
    管æīĢ
    -0.05
     impressions
    -0.05
    çIJĨæŁ¥
    -0.05
    è³ĵ
    -0.05
     nue
    -0.05
    ibal
    -0.05
    å°½æĥħ享åıĹ
    -0.05
    POSITIVE LOGITS
    fli
    0.06
    mith
    0.05
    å¼ķ
    0.05
    ei
    0.05
    ehan
    0.05
    ÑĢÑij
    0.05
    åĨħå¤ĸ
    0.05
     trail
    0.05
    åīįéĢĶ
    0.05
    åij¨åħŃ
    0.05
    Activations Density 0.002%

    No Known Activations