© 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. 19800
    Prev
    Next
    INDEX
    Explanations

    conjunctions or list separators

    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
    1
    -0.05
    -0.05
    4
    -0.05
    lo
    -0.05
     ab
    -0.05
    -
    -0.05
    val
    -0.05
    ä¸ij
    -0.05
    enth
    -0.05
     de
    -0.05
    POSITIVE LOGITS
    лÑİби
    0.08
    doÄŁan
    0.07
     rato
    0.07
    agni
    0.07
    rganization
    0.07
     plata
    0.07
    gangen
    0.07
    beginn
    0.07
    práv
    0.07
    ussin
    0.07
    Activations Density 0.017%

    No Known Activations