© 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. 22241
    Prev
    Next
    INDEX
    Explanations

    closing quote followed by č

    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
    uhn
    -0.07
    REW
    -0.06
    enberg
    -0.06
    ÏĩÏħ
    -0.06
    âu
    -0.05
    κολ
    -0.05
    åĪĻæľī
    -0.05
    ucken
    -0.05
    ä¸įå¿ħè¦ģ
    -0.05
    utori
    -0.05
    POSITIVE LOGITS
    ély
    0.06
    æīĢå¾Ĺ
    0.06
    adi
    0.05
    olino
    0.05
    Lon
    0.05
    plet
    0.05
    鼶
    0.05
    bedo
    0.05
    åѦæ³ķ
    0.05
     fascia
    0.05
    Activations Density 0.036%

    No Known Activations