© 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. 20741
    Prev
    Next
    INDEX
    Explanations

    cron job scheduling

    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
     ÑĤоÑĢ
    -0.06
    çŃĭ
    -0.06
     pup
    -0.05
     prem
    -0.05
    ä¸ĢåĪĩ
    -0.05
    ende
    -0.05
     ì°¸
    -0.05
     Extr
    -0.05
    顺
    -0.05
     Toll
    -0.05
    POSITIVE LOGITS
     suicides
    0.07
    éħįåĶ®
    0.07
    Sparse
    0.06
    Annotations
    0.06
    voja
    0.06
    ownt
    0.06
    çľģçĶµ
    0.06
    åħ¬å¹³ç«ŀäºī
    0.06
    ãĤĴãģĭãģijãģ¦
    0.06
    ç¦ģå¿Į
    0.06
    Activations Density 0.004%

    No Known Activations