© 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. 17991
    Prev
    Next
    INDEX
    Explanations

    misleading information or status

    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
    stva
    -0.07
    rops
    -0.07
    onces
    -0.07
    Ùĩرة
    -0.07
    æŀĹæµ·
    -0.06
    stvo
    -0.06
    ultas
    -0.06
    jav
    -0.06
    å®ĥå°±ä¼ļ
    -0.06
    é¢ĦæľŁ
    -0.06
    POSITIVE LOGITS
     unrecognized
    0.06
     misleading
    0.05
    opf
    0.05
     misplaced
    0.05
     period
    0.05
    ä¸ĢçĽ´è¢«
    0.05
    缮åħī
    0.05
    èĩª
    0.05
     unnoticed
    0.05
    lings
    0.04
    Activations Density 0.075%

    No Known Activations