© 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. 19830
    Prev
    Next
    INDEX
    Explanations

    unanswered questions, owns the, ab Apple

    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
    enders
    -0.06
    press
    -0.05
    俱
    -0.05
     press
    -0.05
    æ¸łéģĵ
    -0.05
     nature
    -0.05
    åķĬ
    -0.05
    ons
    -0.05
    stras
    -0.05
     indes
    -0.05
    POSITIVE LOGITS
    ç»ĨåĪĨ
    0.06
    ç»ĨåĮĸ
    0.06
     absorbing
    0.06
     pinpoint
    0.06
    fine
    0.05
     subdiv
    0.05
    äºĭåīį
    0.05
    ä¸Ģç½ij
    0.05
    纶
    0.05
     subdivisions
    0.05
    Activations Density 0.007%

    No Known Activations