© 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. 18992
    Prev
    Next
    INDEX
    Explanations

    delimiter, terminated, delimited

    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
    estim
    -0.06
    itant
    -0.06
    kort
    -0.06
    urf
    -0.06
    GROUND
    -0.06
     improper
    -0.06
    angun
    -0.06
    ÑĪкÑĥ
    -0.06
    urgical
    -0.06
    umpul
    -0.06
    POSITIVE LOGITS
    读
    0.05
    lott
    0.05
     read
    0.05
     Ñģл
    0.05
    读åĪ°
    0.05
    读åıĸ
    0.05
    ality
    0.05
    ä¸įæŃ¢
    0.05
     reads
    0.05
    æľ¨æľī
    0.05
    Activations Density 0.008%

    No Known Activations