© 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. 17655
    Prev
    Next
    INDEX
    Explanations

    Java programming language

    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
    ä½Ĩä¸įéĻIJäºİ
    -0.08
    rash
    -0.08
    èĥ¤
    -0.07
    axe
    -0.07
    ãĥ£
    -0.07
    azol
    -0.07
    ray
    -0.06
     TouchableOpacity
    -0.06
    ย
    -0.06
    ÙĪÙģØ©
    -0.06
    POSITIVE LOGITS
    à¸ŀลิà¹Ģà¸Ħà¸Ĭัà¸Ļ
    0.06
    ีà¹ĭยว
    0.05
     beginning
    0.05
    çIJħ
    0.05
    ÑĨи
    0.05
     kia
    0.05
     Bieber
    0.05
    æ±½
    0.05
    ìłľ
    0.05
     bedo
    0.05
    Activations Density 0.027%

    No Known Activations