© 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. 20270
    Prev
    Next
    INDEX
    Explanations

    locations and placement

    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
    ìĹŃ
    -0.06
    hil
    -0.05
     Chem
    -0.05
    bü
    -0.05
     proper
    -0.05
    üss
    -0.05
     Proper
    -0.05
     JMP
    -0.05
    -solid
    -0.05
    home
    -0.05
    POSITIVE LOGITS
    istribution
    0.06
    ä¸İ被
    0.06
    ä¸İå½ĵåľ°
    0.06
    ائÙĬØ©
    0.05
    azier
    0.05
    ä¸İä¸ĸçķĮ
    0.05
    å®Ŀå®īåĮº
    0.05
    urous
    0.05
    istics
    0.05
     empl
    0.05
    Activations Density 0.051%

    No Known Activations