© 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. 18692
    Prev
    Next
    INDEX
    Explanations

    x position variables

    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
    ment
    -0.07
    menta
    -0.07
    年以ä¸ĬçļĦ
    -0.06
     بث
    -0.06
    TEE
    -0.06
    sker
    -0.06
     démocr
    -0.06
    menti
    -0.06
    egt
    -0.06
    omor
    -0.05
    POSITIVE LOGITS
    溶
    0.06
     Sole
    0.05
    er
    0.05
    å±ķ
    0.05
    log
    0.05
    çݯèĬĤ
    0.05
    汤
    0.05
    hay
    0.05
    /ext
    0.05
    hai
    0.05
    Activations Density 0.001%

    No Known Activations