© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-4B
    5. 15-RES-MATRYOSHKA-65K
    7. 18342
    Prev
    Next
    INDEX
    Explanations

    descriptive adjectives

    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
    avier
    -0.06
    æ·±å±Ĥ次
    -0.05
     blunt
    -0.05
    大åı¯
    -0.05
    ãģĹãĤĦãģĻãģĦ
    -0.05
    UBE
    -0.05
    ated
    -0.05
    à¸Ńยูà¹Īà¹ģลà¹īว
    -0.05
    åĴĮåľ°æĸ¹
    -0.05
    artz
    -0.05
    POSITIVE LOGITS
    inee
    0.07
    -Con
    0.07
    incon
    0.06
    ozo
    0.06
    olls
    0.06
    èĭŁ
    0.06
    åĽłçĹħ
    0.06
    -con
    0.06
    /con
    0.05
    lessly
    0.05
    Activations Density 0.004%

    No Known Activations