© 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. 20605
    Prev
    Next
    INDEX
    Explanations

    not responding or denied

    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
    åĴĮéĿŀ
    -0.06
     whenever
    -0.06
     priority
    -0.06
    èĬ®
    -0.05
     when
    -0.05
    ä¸İéĿŀ
    -0.05
     scratch
    -0.05
    çł´æµª
    -0.05
    /non
    -0.05
     hv
    -0.05
    POSITIVE LOGITS
     defaults
    0.06
    ิà¹Īà¸ĩ
    0.06
    defaults
    0.06
    åľ¨è¿Ļ段æŶéĹ´
    0.06
    arb
    0.06
    åľ¨è§Ħå®ļæŶéĹ´åĨħ
    0.06
    é»ĺ认
    0.06
    default
    0.06
    .Default
    0.06
     dese
    0.05
    Activations Density 0.043%

    No Known Activations