© 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. 18405
    Prev
    Next
    INDEX
    Explanations

    code execution start

    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
    åĢĻ
    -0.06
    ác
    -0.06
    ack
    -0.06
    CU
    -0.06
    оÑģо
    -0.05
    unt
    -0.05
    ouri
    -0.05
     dah
    -0.05
    ogra
    -0.05
    åıĺåĮĸ
    -0.05
    POSITIVE LOGITS
    _native
    0.05
    ä¸įèĥ½è®©
    0.05
    ional
    0.05
     avv
    0.05
    imon
    0.05
    _wire
    0.05
     condu
    0.05
    request
    0.05
     principles
    0.05
    çIJĨ念
    0.05
    Activations Density 0.028%

    No Known Activations