© 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. 17051
    Prev
    Next
    INDEX
    Explanations

    Let or What followed by numbers

    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
    otty
    -0.06
    ment
    -0.06
    пло
    -0.05
     whichever
    -0.05
    oe
    -0.05
    ssue
    -0.05
    uffer
    -0.05
     tot
    -0.05
     Hadi
    -0.05
    door
    -0.05
    POSITIVE LOGITS
    å®ļ
    0.08
    å®ļäºĨ
    0.06
    ä¼ł
    0.06
    ÄĻc
    0.06
    å®ļçļĦ
    0.06
    å®ļåĬĽ
    0.06
    磼
    0.06
    å®ļ为
    0.06
     liqu
    0.06
    è§ħ
    0.06
    Activations Density 0.003%

    No Known Activations