© 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. 18181
    Prev
    Next
    INDEX
    Explanations

    lifetimes or life

    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
    ÅĤas
    -0.06
     влаÑģ
    -0.06
     ÑģобÑģÑĤвен
    -0.06
    anak
    -0.06
    çļĦéĻĪ
    -0.06
    fertig
    -0.06
    aled
    -0.06
    çĦ¡éľĢ
    -0.06
    è¶Ĭä¾Ĩè¶Ĭå¤ļ
    -0.06
    êng
    -0.06
    POSITIVE LOGITS
     odk
    0.06
    广度
    0.05
     share
    0.05
     ke
    0.05
    ke
    0.05
     physically
    0.05
    idi
    0.05
    æī¿
    0.05
     Prairie
    0.05
     palate
    0.04
    Activations Density 0.002%

    No Known Activations