© 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. 19242
    Prev
    Next
    INDEX
    Explanations

    component composition

    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
    enam
    -0.07
    xde
    -0.06
    ated
    -0.06
     undermin
    -0.06
    uded
    -0.06
    åĴĮè°ĥæķ´
    -0.06
    Laughs
    -0.05
    usions
    -0.05
    xad
    -0.05
    çºĤ
    -0.05
    POSITIVE LOGITS
    lach
    0.06
    ÙĤاطع
    0.06
    ç¾Į
    0.06
    èݹ
    0.05
     scope
    0.05
    licht
    0.05
    ÑĢо
    0.05
    èĢ³
    0.05
    ocratic
    0.05
    å¢Ļä¸Ĭ
    0.05
    Activations Density 0.021%

    No Known Activations