© 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. 16915
    Prev
    Next
    INDEX
    Explanations

    named after or called

    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
    æĥ¯äºĨ
    -0.06
    ulu
    -0.05
     Dom
    -0.05
    ahl
    -0.05
    iled
    -0.05
    coli
    -0.05
    ipation
    -0.05
    вален
    -0.05
    or
    -0.05
     proprietary
    -0.05
    POSITIVE LOGITS
    æķ¦
    0.06
    _modes
    0.06
    çĮĽçĥĪ
    0.06
    çIJ¦
    0.06
     centrally
    0.06
    ãģijãģ©ãģŃ
    0.06
    chenke
    0.05
    鸣
    0.05
    æ¯ĶåĪ©
    0.05
    icule
    0.05
    Activations Density 0.012%

    No Known Activations